audit-plan
Audit a design plan or proposal before any of it is built — decide for each capability whether it is the library's problem or the user's, and if the user's, whether they have the primitives to solve it; enumerate the permanent public surface it would add; verify every load-bearing claim against the real codebase instead of assuming it; and fan out independent per-dimension auditors so a plan is never marked by its own author. Returns a blocking verdict: findings that shrink scope, build a feature where a primitive would do, reinvent a `@langchain/*` capability, encode a policy belonging to the deployment, or commit public API the project cannot later withdraw stop the plan until it is revised or the user explicitly confirms an override, which is recorded in the repo. Use whenever a plan-mode plan or a `docs/proposals/*.md` is about to be approved, implemented, or turned into commits. Enforces AGENTS.md golden rule 1 ("reuse first") at design time, the way `/commit` enforces rule 4 at c
skein-js · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add skein-js/skein-js --skill audit-plan技能说明
name: audit-plan
description: >-
Audit a design plan or proposal before any of it is built — decide for each capability whether
it is the library's problem or the user's, and if the user's, whether they have the primitives
to solve it; enumerate the permanent public surface it would add; verify every load-bearing
claim against the real codebase instead of assuming it; and fan out independent per-dimension
auditors so a plan is never marked by its own author. Returns a blocking verdict: findings that
shrink scope, build a feature where a primitive would do, reinvent a @langchain/* capability,
encode a policy belonging to the deployment, or commit public API the project cannot later
withdraw stop the plan until it is revised or the user explicitly confirms an override, which is
recorded in the repo. Use whenever a plan-mode plan or a docs/proposals/*.md is about to be
approved, implemented, or turned into commits. Enforces AGENTS.md golden rule 1 ("reuse first")
at design time, the way /commit enforces rule 4 at commit time.
/audit-plan — gated design review
skein is published, open source, and used by people who are not in the conversation that produced
the plan. This audit represents them. Run it, revise anything blocking, re-run, then build. It is
the design-time counterpart to /commit: rule 4 keeps red code out of the
repo, this keeps unearned scope and unearned API out of the plan, enforcing
AGENTS.md golden rule 1 and docs/reuse.md.
Public API here is effectively permanent, and that is the stake. nx release versions every
packages/* as a fixed group (nx.json), so one breaking change majors packages
that did not change. The repo's own policy is to rename by alias and @deprecated, never by removal —
and it has honoured that, carrying five live aliases in packages/*/src rather than deleting a name.
So an exported symbol, config key, route or wire field is not a decision that gets revisited later;
it is maintenance surface for as long as the project exists. The question is not "is this a good
idea?" but "are we sure enough to keep it forever?"
The second question is whose problem it is. skein's value is plumbing users cannot write
themselves and the first-party onboarding/integration surface that lets them adopt that plumbing
correctly. An official CLI command, project scaffold, framework generator, or maintained starter
is upstream when it only composes skein's published contracts, teaches secure supported defaults,
and gives the project an upgrade path; the fact that a user could reproduce those files manually
does not make it downstream. Application behavior, business rules, identity policy, and
deployment-specific choices remain the user's problem. For those, the library's job is to make sure
the primitives exist and then get out of the way — a primitive is smaller permanent surface than a
feature, and it fits deployments whose requirements we will never see. Both standards are
empirical, not invented: a store.scope
setting was built and deleted because a handler expresses every policy a setting expresses one of,
and a plan claimed background extraction was server-only when after_seconds plus run-cancel already
made it user-buildable. The burden is on the plan — an auditor that agrees with it still hands in
the rollability table, because the table is the work and agreement is not.
Two things this is not. It does not review whether the plan is correct — that is code review, once there is code. And it is not a vote: findings come from artifacts, never from a show of hands.
1. Resolve the target
In order: an explicit argument; else the harness's active plan file, if it keeps one (Claude Code
writes them to ~/.claude/plans/); else a named docs/proposals/*.md; else the plan just discussed
in conversation — in which case restate it and put the restatement at the top of the report, so the
user can confirm the right thing was audited. If two candidates are plausible, ask rather than
guessing.
Then apply the scope test, which exists to let the audit be small: if the target adds no public surface, no config key and no new user-facing capability — a refactor, a bugfix, a docs change — run only dimensions D and F and say so in the report. An auditor with a mandate and nothing to find invents things, so give it permission to have little to do.
2. Extract the inventory and the claim ledger
Two flat lists, quoted verbatim from the target, with all rationale stripped:
- Capability inventory — each thing the plan proposes to build, one bullet each.
- Claim ledger — every falsifiable assertion about this codebase, about
@langchain/*, or about a provider. "LangGraph has no X", "a user cannot do Y today", "this write is atomic".
Strip the rationale deliberately: an auditor handed the argument for a capability audits the argument instead of the capability.
3. Verify the premises
One subagent, run before the others because its output is their input. Rank the ledger by
load-bearingness — a claim is load-bearing if a phase disappears when it turns out false — take the
top ~10, and probe each with a command whose output is quoted back. Return a fact sheet of
CONFIRMED / FALSIFIED / UNVERIFIABLE, each with its probe.
Use a subagent rather than doing this yourself: when you wrote the plan, you also wrote the premises.
| Claim | Probe |
|---|