Borrowing it
Nothing to install: this file belongs to fulminate-io/knowledge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fulminate-io/knowledge-mcp/main/.claude/skills/revise-plan/SKILL.mdgit clone --depth 1 https://github.com/fulminate-io/knowledge-mcpWrote 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/fulminate-io/knowledge-mcp/revise-plan)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/revise-plan"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/revise-plan/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/fulminate-io/knowledge-mcp/revise-plan"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/revise-plan.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 | $0.00053 | $0.01169 |
| Opus 5 | $0.00026 | $0.00584 |
| Sonnet 5 | $0.00011 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
revise-plan 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 5d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REVISE-PLAN — the revision laws
Measured across this project's own review loops: the majority of later-round findings are located in or caused by the previous round's fix — revisions create the next round's defect surface. These laws exist to make a revision leave the plan STRONGER than the finding found it.
THE FIVE REVISION LAWS
- SELF-EXECUTE EVERY REPAIRED GATE, ALL DIRECTIONS, BEFORE RESUBMIT. A repaired criterion is re-run red (against the violating state), green (against correct/control state), and — where the gate's subject is a container/placement choice — against the plausible-wrong third input. The next reviewer's execution is an adversarial second opinion, never the first run of your repair. Record the runs on the criterion (evidence_red / evidence_green updated to the repaired bytes).
- SWEEP EVERY FIX TO ITS CLASS. A point-fix is not resubmittable. Before resubmit, sweep every sibling sharing the defect's shape — same grepped symbol, anchor style, selector form, stale numeral — and fix or explicitly clear each member. The class the reviewer found one instance of is your enumeration duty now.
- EVERY CORRECTION LANDS AS A GATE, NEVER PROSE ALONE. A hard-won correction written into step prose but not into a criterion is invisible to the implementer and unenforceable by the next audit. If the correction constrains behavior, it gets a criterion (or amends one); prose may explain, never carry.
- THE FINAL PRE-SHIP ROUND IS FULL-SCOPE. Delta re-audits are legitimate mid-loop; the round that precedes ship re-verifies the WHOLE plan — residue outside the delta is exactly what escapes to implementation.
- TERMINATION IS CONVERGENCE, NOT EXHAUSTION. A loop ends when a full-scope round reports zero T1/T2 and no unproven evidence stamps — never because the verdict wording softened or patience ran out.
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.
- 5d ago First seen · 92 lines · 53 tokens per session scan A fe2ef1375e72
revise-plan is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,169 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 2026-09-04.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.