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/authoring-issues-prs/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/authoring-issues-prs)<a href="https://agentmods.dev/skills/pvliesdonk/markdown-vault-mcp/authoring-issues-prs"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/authoring-issues-prs/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/authoring-issues-prs"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/authoring-issues-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 12 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00099 | $0.02273 |
| Opus 5.5 | $0.00040 | $0.00909 |
| Sonnet 5.5 | $0.00020 | $0.00455 |
| Haiku 4.5 | $0.00010 | $0.00227 |
Grade A, and why
authoring-issues-prs 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 4d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- authoring-issues-prs — 100% identical, 110 lines differ
- authoring-issues-prs — 100% identical, 145 lines differ
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring issues and pull requests
CONTRIBUTING.md holds the issue rules, the agent-post footer and the
three-tier routing; AGENTS.md and .github/PULL_REQUEST_TEMPLATE.md hold
the PR rules. This skill adds the order of operations, the sizing
procedure behind the limits AGENTS.md sets, and the API steps issue forms
cannot perform; it states none of the other rules itself.
Procedure
1. Read CONTRIBUTING.md — now, not from memory
Read CONTRIBUTING.md (repository root) before drafting a single sentence,
even if you believe you remember it:
- "Observation, not work order" and "The uncertainty rule" — issue voice
and the
[verified: how]/[unverified]markers. - "One issue, one observed problem" and the "Remove before posting" table — run your draft through the table before submitting.
- "Pull requests" — which
AGENTS.mdsections and template govern a PR, and the merge style. - "Where to send fixes" — the routing walked in step 2.
- "Agent-authored posts" — the footer every post ends with, and how to read earlier posts under the account holder's name (step 8).
Where this skill and CONTRIBUTING.md disagree, the file wins.
2. Route before writing
Decide the repo before writing: ask which file a fix would change, and
look that file up in CONTRIBUTING.md's "Where to send fixes" (library,
template or domain). When the tier is unclear, file where you think it
belongs and say so in the issue with an [unverified] marker.
3. Search for duplicates
Search the target repo's issues — open and closed — before filing:
gh issue list --repo OWNER/REPO --state all --search "<key terms>"
Match on the observation, not the wording. If the problem is already on file, comment on the existing issue rather than opening a twin; if a closed issue shows it regressed, say that in the new issue and link it.
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.
- 4d ago Changed · +14 lines · +13 tokens per session 3f6a008dc135
- 21d ago Changed 555a60725332
- 28d ago Changed · +8 lines 52530c9123d2
- 1mo ago Changed 125868086d92
- 1mo ago Changed · +27 lines cc91cf486d0e
- 1mo ago First seen · 143 lines · 86 tokens per session scan A 539b6aab8e11
authoring-issues-prs is a skill published in the GitHub repository pvliesdonk/markdown-vault-mcp (35 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 2,273 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
Folio Tables
Work with Folio data tables (kind table) through foliotable MCP tools — schema-first, column types, filters, and typical schemas for a risk register, sprint plan, or backlog.
folio-wiki
Search, read and update the team's Folio wiki (pages, data tables, whiteboards, forms, bases, interactive artifacts) through the Folio MCP tools. Use when the task mentions the wiki, Folio, team conventions, runbooks, decisions, release notes or a Folio link, when you should write something down for the team, or when…
release-notes
Compare the repository with the team's Folio wiki and write release notes: read git log since the last tag, read the Roadmap table, create or update a Release notes page and add what the roadmap table is missing. Use when asked for release notes or to sync the wiki with the code.
solomd
Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server. 13 tools including AutoGit per-note history, semantic search, and write-with-sandbox via an accept/reject branch. Includes 11 starter agent recipes (weekly review, todo extract, link suggester, …).
github-issue-lifecycle
A GitHub Issue workflow for taking a code change from request to review, approval, testing, and closure. It can also keep a GitHub Project board—the task board attached to a repository—in sync.
Folio Boards
Generate Excalidraw boards with createboard's sketch DSL and tidy EXISTING boards with boardops (align/distribute/autolayout) — layout method, palette, worked examples.