Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vasuag09/harness-claude --skill plan-checkgit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vasuag09/harness-claude/plan-check)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/plan-check"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/plan-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vasuag09/harness-claude/plan-check"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/plan-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.00752 |
| Opus 5 | $0.00037 | $0.00376 |
| Sonnet 5 | $0.00015 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
plan-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan-check — gate the plan before building
Goal: catch a broken plan before an executor acts on it. An ambiguous or incomplete plan produces an executor that guesses; parallel executors guessing differently about the same file produce conflicts. Cheaper to fix the plan now than to unwind code later.
This is the plan-phase counterpart to /harness-claude:review — same adversarial stance, one step
earlier. It is read-only: it reports, it does not edit the plan.
Do this
- Load the artifacts:
.claude/planning/<slug>/PLAN.mdandSPEC.md(slug is in.claude/STATE.md). If there's noPLAN.mdon disk (trivial/inline work), review the plan from the conversation instead — the checks are the same. - Delegate to the
harness-claude:planneragent in a check pass (read-only — pass it the plan, the spec, and the objective: "find why this plan fails before we build it"). Get back a summary with severities, not a raw dump. - Check the plan across three dimensions:
- Criteria coverage — does every
AC-ninSPEC.mdmap to at least one task'saddresses:? Name any uncovered criterion. - Scope — does any task do work no criterion asked for (scope creep), or is any in-scope item unplanned? Flag both directions.
- Task independence — for tasks meant to run in parallel (same wave / no
depends_onbetween them), are the write-sets pairwise disjoint? Aredepends_onedges acyclic and complete (no task reads another's output without declaring it)? Overlapping write-sets or a missing edge is a correctness bug.
- Criteria coverage — does every
- Red-team it: assume the plan already failed in execution and ask why. Attack hidden assumptions, not just the obvious risks.
- If findings warrant a revision, hand them back to
/harness-claude:planand re-check — loop ≤ 3 times (per rules/agents.md), then accept or escalate to the user.
Output
A findings list, most-severe first, each with a severity:
| Severity | Meaning | Action |
|---|---|---|
| Critical | The plan cannot satisfy a criterion, or parallel tasks collide on a file | BLOCK — fix the plan before /harness-claude:implement |
| High | Likely bug or significant gap | Fix before building |
| Medium | Maintainability / clarity concern | Fix when reasonable |
| Low | Minor suggestion | Optional |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 55 lines · 75 tokens per session scan A 2e3a6cccd856
plan-check is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 752 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.