cure

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/cure

/cure

Use this skill after
/age
, failed validation, or user-selected review findings need to be fixed and prepared for shipping.
当/age报告、验证失败或用户指定的评审问题需要修复并准备发布时,使用此技能。

Inputs

输入

Accept any of: a
/age
slug (
/cure <slug>
reads
.cheese/age/<slug>.md
), a pasted findings list, a CI failure summary, or a scoped instruction like "fix the high-severity age findings". When
/age
or
/affinage
hands off a pre-locked selection (canonical format:
references/selection.md#handoff-from-age
), adopt it and go straight to apply. Called bare, apply the recommended composite (
all-medium, cheap
) per
references/selection.md
, which also defines the gate conditions.
Age reports may predate the severity-rubric revision and lack per-finding sub-fields or
confidence
. Read
references/selection.md
§ Older report shape before selecting from such a report — it defines the inference and toleration rules; never reject a report for missing sub-fields.
Optional flags:
  • --safe
    — re-introduce the selection and terminal publication handoff gates.
  • --open-pr
    — after a clean cure, allow terminal
    /plate
    publication when no PR exists.
  • --auto
    — autonomous mode (propagated from
    /cook --auto
    ). Skips user selection; requires
    --stake <floor>
    , and
    /cook --auto
    always passes
    medium+
    . Auto-selection rules:
    references/selection.md
    ; pass-cap and revert behaviour:
    ## Auto mode
    below.
  • --stake <floor>
    — with
    --auto
    only, ignored otherwise. Severity floor:
    blocker
    ,
    high
    ,
    medium+
    , or
    all
    ; definitions and the
    medium+
    cheap-lows rule live in
    references/selection.md
    § Auto-mode selection.
  • --hard
    — propagate the metacognitive-gate flag to terminal
    /plate
    ; see
    ## --hard mode
    .
Portability reference:
../cheese/references/harness-portability.md
. It covers helper resolution, sub-agent dispatch, GitHub operations, and handoff transitions; prefer the bundled or repo-local helper first, and treat
${CLAUDE_SKILL_DIR}
as optional host-provided fallback. The handoff blocks below are the portable contract; slash commands are host renderings, not the control model.
接受以下任意输入:/age报告的slug(
/cure <slug>
会读取
.cheese/age/<slug>.md
)、粘贴的问题列表、CI失败总结,或类似“修复/age报告中的高严重性问题”这类限定性指令。当/age或/affinage传递预先锁定的选择内容(标准格式:
references/selection.md#handoff-from-age
)时,直接采用该内容并开始修复。若未指定输入,则按照
references/selection.md
中的推荐组合(
all-medium, cheap
)执行,该文件同时定义了验证门禁条件。
部分/age报告可能早于严重性规则修订,缺少每个问题的子字段或
confidence
字段。从这类报告中选择问题前,请先阅读
references/selection.md
中的「旧版报告格式」章节,其中定义了推断和容错规则;请勿因缺少子字段而拒绝报告。
可选参数:
  • --safe
    — 重新启用选择环节和最终发布的交接门禁。
  • --open-pr
    — 修复完成后,若不存在PR,则允许调用/plate进行最终发布。
  • --auto
    — 自主模式(从
    /cook --auto
    继承)。跳过用户选择环节;需配合
    --stake <floor>
    使用,且
    /cook --auto
    始终传递
    medium+
    参数。自动选择规则参见
    references/selection.md
    ;传递上限和回退行为参见下文「## 自主模式」。
  • --stake <floor>
    — 仅在
    --auto
    模式下生效,其他模式下忽略。严重性下限可选:
    blocker
    high
    medium+
    all
    ;定义及
    medium+
    的低成本规则参见
    references/selection.md
    中的「自主模式选择」章节。
  • --hard
    — 将元认知门禁参数传递给最终的/plate;参见「## --hard模式」。
可移植性参考:
../cheese/references/harness-portability.md
。该文档涵盖了助手解析、子Agent调度、GitHub操作及交接流程;优先使用捆绑或仓库本地的助手,将
${CLAUDE_SKILL_DIR}
视为可选的宿主提供的备用路径。 以下交接模块是可移植的契约;斜杠命令是宿主层面的呈现形式,而非控制模型。

Flow

流程

  1. Load — read the findings (markdown, not JSON sidecars).
  2. Select — adopt any pre-locked handoff from
    /age
    /
    /affinage
    ; otherwise apply the recommended composite. See
    references/selection.md
    for the default rule, recognized verbs, and gate conditions. To expand a user-supplied verb to finding ids:
    python3 shared/scripts/findings_cli.py parse-selection --report <path> --selection "<verb>"
    If the host only ships the bundle,
    python3 ${CLAUDE_SKILL_DIR}/scripts/common.pyz findings_cli parse-selection ...
    is the fallback.
  3. Apply — fix one logical group at a time: re-confirm the anchor through a fresh bounded read, then apply a stale-safe write from a compatible backend family.
  4. Validate — run the narrowest tests that prove each fix, then any relevant project-wide gates (lint, typecheck, build). When the handoff carries a recorded
    baseline:
    block, classify gate failures against it per
    ../cook/references/quality-gates.md
    : identical failures do not block a clean cure or trigger a halt; only new or changed failures are cure's to fix.
  5. Taste-test (behavioural fixes only) — for a behavioural fix (production logic or public surface), run the fresh-context taste-test before the handoff slug: dispatch the read-only
    reviewer
    phase-agent (model pinned to opus) over the cure diff with cook's lenses, or fall back to the inline self-check if unavailable. Mechanical fixes (formatting, comment, import, no-logic rename) skip this. Pipe a
    revise
    into a bounded corrective pass; a Locked-decision
    halt
    stops for a human. (A coder-nested cure defers the authoritative pass to the orchestrator.)
  6. Domain-model correction (diff-touched terms only) — after the cook's fixes land, correct diff-touched domain-model terms (never a free rewrite). Read
    references/domain-model-correction.md
    before this step — it defines the store resolution, the entry format, and the hard rule against reversing a mold-locked canonical term.
  7. Re-review hand-off — recommend
    /age --scope <touched-path>
    so review runs through the proper skill rather than reimplementing it inline.
    /cure
    does not re-grade its own work. If the user picks re-age, the resulting report can feed a fresh
    /cure
    invocation.
  8. Ship report — what changed, checks run, deferred items, residual risks. Write the handoff slug at the top of
    .cheese/cure/<slug>.md
    (see
    ## Handoff slug
    below) so the chain (and
    /cook
    's fan pathway) can read the outcome without re-parsing the full report.
  9. Plate / hand off — on a clean cure, dispatch
    /plate
    per
    ## Handoff
    .
  1. 加载 — 读取问题内容(markdown格式,而非JSON副文件)。
  2. 选择 — 采用/age或/affinage传递的任何预先锁定的选择内容;否则应用推荐组合。默认规则、可识别动词及门禁条件参见
    references/selection.md
    。如需将用户提供的动词扩展为问题ID:
    python3 shared/scripts/findings_cli.py parse-selection --report <path> --selection "<verb>"
    若宿主仅提供捆绑包,则使用备用命令:
    python3 ${CLAUDE_SKILL_DIR}/scripts/common.pyz findings_cli parse-selection ...
  3. 修复 — 每次修复一个逻辑组:通过新的有限读取重新确认锚点,然后从兼容的后端库执行防过期写入。
  4. 验证 — 运行能证明每个修复有效的最窄范围测试,再运行任何相关的项目级门禁(代码检查、类型校验、构建)。当交接内容包含已记录的
    baseline:
    模块时,需对照
    ../cook/references/quality-gates.md
    对门禁失败进行分类:与基线完全一致的失败不会阻碍修复完成或触发终止;仅新出现或变更的失败需要/cure修复。
  5. 尝试验证(仅针对行为修复) — 对于行为修复(生产逻辑或公共接口),在生成交接slug前运行上下文尝试验证:通过cook的视角,将修复差异交由只读的
    reviewer
    阶段Agent(模型固定为opus)进行评审;若该Agent不可用,则退化为内联自检查。机械修复(格式调整、注释修改、导入优化、无逻辑重命名)可跳过此步骤。若发现问题,则执行
    revise
    进行有限的修正;若收到锁定决策
    halt
    ,则停止操作等待人工介入。(嵌套在编码流程中的修复会将权威验证环节委托给编排器。)
  6. 领域模型修正(仅针对差异涉及的术语) — 在cook的修复完成后,修正差异涉及的领域模型术语(禁止无约束重写)。执行此步骤前,请阅读
    references/domain-model-correction.md
    ,其中定义了存储解析、条目格式,以及禁止修改已锁定的标准术语的严格规则。
  7. 交接评审 — 推荐调用
    /age --scope <touched-path>
    ,使评审通过合适的技能进行,而非内联重新实现。/cure不会重新评估自身的修复工作。若用户选择重新评审,生成的报告可用于新的/cure调用。
  8. 发布报告 — 记录变更内容、运行的检查、延迟处理的项及剩余风险。在
    .cheese/cure/<slug>.md
    顶部写入交接slug(参见下文「## 交接slug」),以便流程链(及/cook的分支路径)无需重新解析完整报告即可读取结果。
  9. 交付/plate — 修复完成后,按照「## 交接」部分的规则调用/plate。

Preferred tools and fallbacks

首选工具及备选方案

Call source-code search, read, and write backends directly according to
code-intelligence-routing.md
.
Beyond source-code routing there are cure-specific tools:
NeedPreferFallback
Understanding findings
/age
report plus touched diff/test context
diff, touched files, tests
CI and PR context
gh
local test output or user-provided logs
Diffs
delta
plain
git diff
Conflict resolutionmergirafmanual resolution with targeted tests
Code navigationsemantic symbol search, then caller searchLSP or bounded native search; report precision loss
Read before editfresh bounded read from the write backend familyanother snapshot-capable bounded read; re-read if anchors are incompatible
If a preferred tool is missing, continue with the fallback. If a missing tool prevents safe application, stop and explain the blocker.
根据
code-intelligence-routing.md
直接调用源代码搜索、读取及写入后端。
除源代码路由外,还有/cure专用工具:
需求首选工具备选方案
理解问题/age报告 + 涉及的差异/测试上下文差异文件、涉及的文件、测试用例
CI及PR上下文
gh
本地测试输出或用户提供的日志
差异展示
delta
原生
git diff
冲突解决mergiraf配合针对性测试手动解决
代码导航语义符号搜索,其次是调用方搜索LSP或有限原生搜索;记录精度损失
编辑前读取从写入后端库获取最新的有限读取结果其他支持快照的有限读取;若锚点不兼容则重新读取
若首选工具缺失,则使用备选方案。若缺失的工具会阻碍安全修复,则停止操作并说明阻塞原因。

Validation

验证

Run the narrowest tests that prove the fix, then any relevant existing wider gates. If a gate is unavailable, record why. Do not declare ready when selected findings remain unresolved.
Applied requires its proving test green (Iron Law — see
references/cure-discipline.md
).
clean cure — ≥1 fix applied, all gates green (identical recorded
baseline:
failures don't count against green — see
../cook/references/quality-gates.md
), no false-premise halt. To map the post-cure gate booleans to a readiness verdict (agent judges the booleans; the CLI maps them):
python3 shared/scripts/gates_cli.py classify \
  --press-status <label> \
  [--hard-floor-met] [--has-open-level-1-or-2] [--has-open-level-3] [--has-open-level-4-or-5] [--any-spinning]
If the host only ships the bundle,
python3 ${CLAUDE_SKILL_DIR}/scripts/common.pyz gates_cli classify ...
is the fallback.
运行能证明修复有效的最窄范围测试,再运行任何相关的现有全局门禁。若门禁不可用,记录原因。当仍有未解决的指定问题时,不得宣布修复完成。
修复必须通过对应的验证测试(铁律 — 参见
references/cure-discipline.md
)。
修复完成 — 至少应用了1项修复,所有门禁均通过(与已记录的
baseline:
完全一致的失败不计入失败 — 参见
../cook/references/quality-gates.md
),无错误前提导致的终止。如需将修复后的门禁状态映射为就绪 verdict(Agent判断状态;CLI负责映射):
python3 shared/scripts/gates_cli.py classify \
  --press-status <label> \
  [--hard-floor-met] [--has-open-level-1-or-2] [--has-open-level-3] [--has-open-level-4-or-5] [--any-spinning]
若宿主仅提供捆绑包,则使用备用命令:
python3 ${CLAUDE_SKILL_DIR}/scripts/common.pyz gates_cli classify ...

Handoff slug

交接slug

Write the cure report to
.cheese/cure/<slug>.md
with a minimum handoff slug at the top so
/cook
's fan pathway and
/cheese --continue
can chain without re-parsing the full report:
markdown
status: ok | halt: <one-line reason>
next: age | done
artifact: <path-if-any>
baseline: none | <recorded baseline block copied from the upstream handoff — see ../cook/references/quality-gates.md>
<one-line orientation: what cure applied or deferred>
status: ok
when at least one finding applied cleanly (or no findings met the severity floor in
--auto
mode);
status: halt: <reason>
when every selected fix failed the revert/keep evaluation or a project-wide gate cannot be made green.
next:
is
age
whenever re-review should follow — that is the autonomous-chain default and the standard interactive recommendation.
next:
is
done
only when invoked interactively without
--auto
and the user explicitly opts out of re-review. Cure does not track which pass it is on; the two-cure-pass cap is enforced by
/age --auto
's third invocation, not by cure.
将修复报告写入
.cheese/cure/<slug>.md
,并在顶部添加最小化交接slug,以便/cook的分支路径和
/cheese --continue
无需重新解析完整报告即可继续流程:
markdown
status: ok | halt: <单行原因>
next: age | done
artifact: <路径(如有)>
baseline: none | <从上游交接内容复制的已记录基线模块 — 参见../cook/references/quality-gates.md>
<单行说明:已应用或延迟处理的修复内容>
当至少一项问题被成功修复(或在
--auto
模式下无问题符合严重性下限)时,
status: ok
;当所有选定的修复均未通过回退/保留评估,或项目级门禁无法通过时,
status: halt: <reason>
next:
默认设为
age
,即需要进行重新评审 — 这是自主流程链的默认设置,也是交互式操作的标准推荐。仅当以交互式方式调用且未使用
--auto
用户明确选择不进行重新评审时,
next:
才设为
done
。/cure不跟踪当前是第几轮修复;两轮修复上限由
/age --auto
的第三次调用 enforce,而非/cure。

Output

输出

Cross-cutting house style and citation form:
../cheese/references/formatting.md
.
The cure report body lives below the handoff slug in the same file at
.cheese/cure/<slug>.md
:
markdown
undefined
通用格式及引用规范:
../cheese/references/formatting.md
修复报告主体位于交接slug下方,同一文件
.cheese/cure/<slug>.md
中:
markdown
undefined

Cure Report

修复报告

Applied

已应用修复

  • <finding>: <fix summary>
  • <问题>: <修复摘要>

Deferred

延迟处理项

  • <finding>: <reason>
  • <问题>: <原因>

Checks

检查结果

  • <command>: <pass|fail|skipped with reason>
  • <命令>: <通过|失败|跳过(原因)>

Re-review

重新评审建议

  • Remaining risk:
  • Suggested next step:
    /age --scope <touched-path>
    to verify the fixes, or
    /plate
    to commit/publish.
undefined
  • 剩余风险:
  • 建议下一步操作:调用
    /age --scope <touched-path>
    验证修复,或调用
    /plate
    提交/发布。
undefined

Handoff

交接

Pipeline: culture → mold → cook → press → age → [cure] → plate
After the cure report is rendered, cure decides whether to dispatch
/plate
or ask. On a clean cure (see Validation), the default carries work to an already-open PR without another gate.
--safe
re-introduces the handoff gate.
When the run was chained from
/affinage
(
handoff_context.source_skill: /affinage
), cure never dispatches
/plate
— it applies its fixes, runs the auto-mode
/age --scope
loop where applicable, and returns so
/affinage
can post its GitHub replies (final writes) before owning terminal
/plate
.
Default (no
--safe
) — plate the work:
  • With an open PR (
    gh pr view
    ), dispatch
    /plate [--hard]
    for its final writing gate, commit, topology-aware update, and publication (Rule 11 authorizes the update).
  • With no open PR:
    --open-pr
    dispatches
    /plate [--hard]
    — explicit topology choices and obviously cohesive work proceed without asking, while stack-sized or ambiguous work asks before commit or branch-layout mutation. Without
    --open-pr
    , leave the remote untouched and finish with
    no open PR — pass --open-pr or run /plate
    .
  • After publication lands, run § Post-PR learnings write-back below.
  • If the cure was not clean, skip
    /plate
    ; mention the blocker and stop.
--safe
— ask via the shared handoff gate
in
../cheese/references/handoff-gate.md
. Default options:
  • Re-review the touched code (recommended when fixes escaped the finding hunk)
    /age --scope <touched-path>
    .
  • Plate it — commit and open or update the PR
    /plate [--hard]
    .
  • Checkpoint & stop (
    /wheypoint
    ) or Stop (dispatch none).
Pre-select Plate it only when all selected findings applied cleanly and gates passed. Never dispatch before selection; run the selected command immediately.
流程管线:culture → mold → cook → press → age → [cure] → plate
修复报告生成后,/cure决定是否调用/plate或询问用户。在修复完成(参见验证部分)的情况下,默认会将工作传递至已打开的PR,无需额外门禁。
--safe
参数会重新启用交接门禁。
当从/affinage链式调用时(
handoff_context.source_skill: /affinage
),/cure绝不调用/plate — 仅应用修复,在适用时运行自主模式的
/age --scope
循环,然后返回,以便/affinage在执行最终的/plate发布前完成GitHub回复(最终写入)。
默认(无
--safe
)— 交付/plate:
  • 若存在打开的PR(通过
    gh pr view
    确认),调用
    /plate [--hard]
    执行最终写入门禁、提交、拓扑感知更新及发布(规则11授权更新)。
  • 若不存在打开的PR:
    --open-pr
    参数会触发
    /plate [--hard]
    调用 — 明确的拓扑选择及明显连贯的工作无需询问即可进行,而涉及栈大小或模糊的工作在提交或分支布局变更前会询问用户。若未使用
    --open-pr
    ,则不修改远程仓库,最终提示
    no open PR — pass --open-pr or run /plate
  • 发布完成后,执行下文**§ PR发布后经验回写**。
  • 若未完成修复,则跳过/plate;提及阻塞原因并停止操作。
--safe
— 通过共享交接门禁询问
,参见
../cheese/references/handoff-gate.md
。默认选项:
  • 重新评审涉及的代码 (当修复超出问题范围时推荐)
    /age --scope <touched-path>
  • 交付 — 提交并打开或更新PR
    /plate [--hard]
  • 检查点并停止
    /wheypoint
    )或 停止(不调用任何命令)。
仅当所有选定问题均被成功修复且门禁通过时,才预先选择交付选项。选择完成后立即执行选定的命令,不得提前调用。

Post-PR learnings write-back

PR发布后经验回写

After any path that publishes to a PR — the default
/plate
dispatch, an
--open-pr
new PR, the
--safe
Plate it selection, or the auto-mode terminal publication — read
references/post-pr-writeback.md
before writing back. It defines the write-back candidates (upstream
durable_flags
+ new-since-curdle ADRs), the
/wiki-ingest
writer with its file-fallback degrade, the publication-owner exception, and the "nothing to record" case.
在任何发布至PR的路径之后 — 默认的/plate调用、
--open-pr
新建PR、
--safe
模式下选择交付,或自主模式的最终发布 — 执行回写前请阅读
references/post-pr-writeback.md
。该文档定义了回写候选内容(上游
durable_flags
+ 自curdle以来新增的ADR)、带文件降级备选的
/wiki-ingest
写入器、发布所有者例外情况,以及“无内容可记录”的场景。

--hard mode

--hard模式

/cure --hard
propagates
--hard
to
/plate
, which completes and verifies every durable write, then gives
/hard-cheese
the final artifact inventory and proceeds only on pass. Re-review, checkpoint, and stop choices skip the gate. Mechanism:
skills/hard-cheese/SKILL.md
; composition:
../hard-cheese/references/composition.md
.
/cure --hard
会将
--hard
参数传递给/plate,后者会完成并验证所有持久化写入,然后将最终工件清单交给
/hard-cheese
,仅在通过时继续执行。重新评审、检查点及停止选项会跳过该门禁。机制参见:
skills/hard-cheese/SKILL.md
;组合规则参见:
../hard-cheese/references/composition.md

Auto mode

自主模式

When invoked with
--auto --stake <floor>
, skip the selection list and the handoff gate, auto-select every finding meeting the severity floor (
references/selection.md
§ Auto-mode selection), apply and validate each one — reverting and deferring on breakage — then invoke
/age --scope <touched-paths> --auto
(forwarding
--open-pr
when in scope) so the chain re-reviews;
/age --auto
owns the two-pass cap. On a terminal
next: done
, dispatch
/plate
once and run the § Post-PR learnings write-back above.
Read
references/auto-mode.md
before running this mode — it defines the empty-floor case, the
--auto --hard
puncture clause, and the cook fan-pathway sub-agent exceptions (single-curd chain and wave-curd worker) that suppress terminal
/plate
.
当使用
--auto --stake <floor>
调用时,跳过选择列表和交接门禁,自动选择所有符合严重性下限的问题(参见
references/selection.md
中的「自主模式选择」章节),逐一应用并验证 — 若出现问题则回退并延迟处理 — 然后调用
/age --scope <touched-paths> --auto
(在范围内时传递
--open-pr
参数)进行重新评审;
/age --auto
负责控制两轮修复上限。当最终
next: done
时,调用/plate一次并执行上文**§ PR发布后经验回写**。
运行此模式前请阅读
references/auto-mode.md
,其中定义了无下限场景、
--auto --hard
突破条款,以及抑制最终/plate调用的cook分支路径子Agent例外情况(单一curd链和wave-curd worker)。

Rules

规则

  • Default to the recommended composite (or
    /age
    /
    /affinage
    's locked selection);
    --safe
    re-introduces the gate. A false-premise or sprawling/structural finding still pauses for a decision regardless of mode.
  • Keep fixes scoped to selected (or auto-selected) findings. Baseline-identical gate failures are never cure's to fix (Flow step 4).
  • Do not hide failed or skipped checks. In auto mode, reverted findings go under
    ### Deferred
    , never silently dropped.
  • Publication contract — existing PR authorization,
    --open-pr
    ,
    --safe
    , and never publishing an unclean cure: see
    ## Handoff
    .
  • If a selected finding rests on a false premise (the
    /age
    claim is wrong, or the diff already addresses it), stop and surface the premise before applying. Disagreeing with the report is allowed; silently working around it is not.
  • Apply the shared voice kernel (lives at
    ../age/references/voice.md
    ): lead the cure report with what was applied, flag residual risk as
    certain | speculating | don't know
    , agree when the diff is fine without manufacturing follow-ups.
  • Verification before
    status: ok
    :
    before writing
    status: ok
    in the handoff slug, (1) identify the gate command, (2) run it fresh in the same turn, (3) read the full output, (4) only then claim. Hedging words (
    should
    ,
    probably
    ,
    I think
    ) are banned in completion claims — state what the gate output showed, not what you expect it to show.
  • 默认使用推荐组合(或/age/affinage的锁定选择内容);
    --safe
    参数会重新启用门禁。无论何种模式,若存在错误前提或范围过大/结构性问题,仍需暂停等待决策。
  • 修复范围仅限选定(或自动选定)的问题。与基线一致的门禁失败无需/cure修复(流程步骤4)。
  • 不得隐藏失败或跳过的检查。在自主模式下,回退的问题需归入
    ### 延迟处理项
    ,不得静默丢弃。
  • 发布契约 — 现有PR授权、
    --open-pr
    --safe
    ,且绝不发布未完成的修复:参见「## 交接」部分。
  • 若选定的问题基于错误前提(/age报告有误,或差异已解决该问题),则停止操作并在修复前指出该前提。允许对报告提出异议;禁止静默规避。
  • 应用共享语音内核(位于
    ../age/references/voice.md
    ):修复报告开头先说明已应用的修复,将剩余风险标记为
    certain | speculating | don't know
    ,若差异无问题则直接确认,无需制造后续任务。
  • status: ok
    前的验证
    :在交接slug中写入
    status: ok
    前,需(1)确定门禁命令,(2)在同一轮操作中重新运行该命令,(3)读取完整输出,(4)再进行声明。完成声明中禁止使用模糊词汇(
    should
    probably
    I think
    ) — 需说明门禁输出的实际结果,而非预期结果。

Discipline

规范

Read
references/cure-discipline.md
before applying any fix — it holds the Iron Law, Red Flags, and the fix-application Rationalization table.
应用任何修复前,请阅读
references/cure-discipline.md
,其中包含铁律、警示信号及修复应用合理性表格。

Agent resolution

Agent解析

Resolve fix application through
../cheese/references/agent-resolution.md
.
WorkPreferred typesPermissions/isolationMinimum powerEffortFallback
Apply selected findingscoderwrite, isolated-worktreedefaulthighcompatible coder, then general
The canonical cure handoff carries the shared
agent_resolution
block.
通过
../cheese/references/agent-resolution.md
解析修复应用任务。
工作内容首选Agent类型权限/隔离最低权限工作量备选方案
应用选定问题的修复coder写入权限、隔离工作树默认兼容的coder,其次是通用Agent
标准的/cure交接内容包含共享的
agent_resolution
模块。