Borrowing it
Nothing to install: this file belongs to pvliesdonk/markdown-vault-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/pvliesdonk/markdown-vault-mcp/main/.agents/skills/self-reviewing/SKILL.mdgit clone --depth 1 https://github.com/pvliesdonk/markdown-vault-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/pvliesdonk/markdown-vault-mcp/self-reviewing)<a href="https://agentmods.dev/skills/pvliesdonk/markdown-vault-mcp/self-reviewing"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/self-reviewing/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/pvliesdonk/markdown-vault-mcp/self-reviewing"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/self-reviewing.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 | $0.00069 | $0.03500 |
| Opus 5.5 | $0.00028 | $0.01400 |
| Sonnet 5.5 | $0.00014 | $0.00700 |
| Haiku 4.5 | $0.00007 | $0.00350 |
Grade A, and why
self-reviewing 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 yesterday.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- self-reviewing — 94% identical, 35 lines differ
- self-reviewing — 94% identical, 35 lines differ
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-review
This skill is the local self-review a change gets before its diff becomes
someone else's problem: before a reviewer reads it, before a hosted bot
spends the maintainer's tokens on it, before a fix costs a public push.
It produces a findings report, not a verdict. The self-review
pre-push hook requires only that a review of the pushed commit is recorded,
not that it found nothing; deterministic CI remains the only merge gate.
What it asks instead is honest convergence:
every finding you report gets fixed or explicitly justified, in writing,
before the push.
The review confirms preparation; it rarely discovers. Every criterion below is derived from files already open to you — the rules files, the diff, the code's own comments, the git history — so a clean first pass over a diff you wrote carefully is the normal outcome, not a lucky one.
When to run
- Before
gh pr create(or your agent's equivalent) on a fresh branch. - Before flipping a draft PR to ready.
- Before any push that updates a branch with an open PR.
- On request, against any named PR, branch, or range.
Small diffs are cheap to review; "docs-only" and "obvious" diffs are where contradicted comments and rule violations hide. Run it anyway.
Select the range
Review the cumulative diff — the same one every post-push reviewer sees — never "since my last push".
- Resolve the base ref, in this order of authority:
- the base the invoker explicitly named — an explicit instruction beats recorded metadata (a stacked PR may need a comparison GitHub's recorded base does not give);
- otherwise the PR's actual base branch, when a PR exists
(
gh pr view --json baseRefName); - only as fallback, derive it: the nearest of
origin/<default>,origin/release/*andorigin/integration/*by ancestry (the same derivationscripts/structural_gate.shuses). Never assumemain: a PR targetingrelease/X.Yor a stacked PR reviewed against the default branch sweeps in the base branch's whole divergence or misses the backport's scope. Anintegration/<epic>→mainPR is the one exception to reviewing the whole range as new: every child was reviewed on its way into the integration branch. Review what those reviews could not see — the conflict resolutions in each merge ofmain(git log --remerge-diff --merges "origin/$BASE_REF..HEAD", git 2.36+), semantic conflicts withmain, whether the children fit together and the docs describe the finished result, and the release impact (breaking markers, theCloseslines).docs/contribute/integration-branches.mdcovers the rebased case.
- Compute and check the endpoints before reviewing:
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.
- yesterday Changed · +19 lines 823b86b37019
- 18d ago Changed 2bbdfe125cdb
- 24d ago Changed 1a80b12b6bb8
- 25d ago Changed · +9 lines 3dda2d82aeb3
- 28d ago First seen · 265 lines · 69 tokens per session scan A ccc85992294c
self-reviewing is a skill published in the GitHub repository pvliesdonk/markdown-vault-mcp (35 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 3,500 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
docs-rag
Use when a project's markdown docs, specs, ADRs or decision logs need to be searchable by meaning from the agent, when a searchnotes tool (docs-rag-mcp) is connected, when its results carry labels like [semantic 0.71], [both], [exact match] or [superseded → ...], when it answers "No relevant results", or when a…
mnemonic
Search local indexed markdown knowledge bases. Use when the user asks to find notes, dig up a concept from personal docs, cross-reference ideas across wikis, or answer from indexed local files. Triggers on "look up in notes", "search my docs", "what did I write about", "find in my vault", "check my index", "retrieve…
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
siyuan-plugin-development
Official frontend plugin development workflow. After the user explicitly opts in, clarify missing requirements, confirm a short plan, implement in a managed copy, verify, and package. Installation and activation require separate authorization.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…