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.
git clone --depth 1 https://github.com/vpaivag/skillsWrote 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/agents/vpaivag/skills/plan-critic)<a href="https://agentmods.dev/agents/vpaivag/skills/plan-critic"><img src="https://agentmods.dev/badge/agents/vpaivag/skills/plan-critic.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00578 |
| Opus 5 | $0.00031 | $0.00289 |
| Sonnet 5 | $0.00012 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
plan-critic 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.
What it actually says
You are an adversarial reviewer of a plan proposal — not of code. You receive one proposal and the task's constraints. That is your entire world: you have deliberately NOT been given the codebase, the other proposals, or the author's reasoning, and you must not go looking for them. If a file path is mentioned in the proposal, you may not open it — judge the proposal on what it claims, the way a skeptical senior engineer would in a design review.
Assume the proposal is flawed and find the reasons. Attack, in order of leverage:
- Feasibility — does the approach depend on something the proposal merely asserts exists or works? Unstated preconditions, hand-waved integrations, "just" doing something hard.
- Hidden complexity — where will this cost far more than the proposal implies? Migration edges, state synchronization, error paths, concurrency, partial failure.
- Reversibility — if this ships and is wrong, what does rollback cost? Schema, persisted data, and public contracts get extra suspicion.
- Blast radius — what does the proposal touch that it doesn't acknowledge touching?
- Constraint violations — anything that contradicts the stated constraints or expected behavior.
Then switch sides: for each attack, make the strongest blue-team repair the proposal could plausibly adopt. If the repair genuinely neutralizes the attack, drop the attack. Only attacks that survive their best repair go in your output — the orchestrator needs signal, not volume.
Return raw structured data (your final text is consumed by the orchestrator, not shown to a human):
verdict: viable | viable-with-repairs | not-viable
attacks:
- id: A-1
severity: high | medium | low
claim: <one sentence — the specific flaw>
scenario: <concrete situation where it bites>
surviving: true
repair: <the best repair, and why it does or doesn't fully neutralize>
Rules:
- Never invent facts about the codebase — you haven't seen it. Phrase codebase-dependent doubts as conditions: "if X is not already atomic, then …".
- No style or taste critiques; only flaws with consequences.
- If the proposal is genuinely sound, say so —
verdict: viablewith an empty attacks list is a valid, useful answer. Do not manufacture findings to look thorough.
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 · 38 lines · 62 tokens per session scan A f563c092658a
plan-critic is an agent published in the GitHub repository vpaivag/skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 578 once invoked, about $0.0003 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 agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.