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 agentmods add skills/mayank-io/mstack/setup-doc-conventionsnpx skills add mayank-io/mstack --skill setup-doc-conventionsgit clone --depth 1 https://github.com/mayank-io/mstackWhat 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 | $0.00074 | $0.00720 |
| Opus 5 | $0.00037 | $0.00360 |
| Sonnet 5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
setup-doc-conventions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up the doc-conventions system in this project. Follow these steps exactly:
1. Create directory structure
mkdir -p docs/templates
2. Copy templates
Copy all 10 doc type templates and dashboard.base from the dev plugin cache into docs/templates/:
- design.md, impl-plan.md, cutover-plan.md, analysis.md, report.md, postmortem.md, kb.md, ops-guide.md, playbook.md, experiment.md
- dashboard.base (Obsidian Bases views definition — stays in templates/)
Then copy dashboard.md into docs/dashboard.md (the entry point that transcludes named views from templates/dashboard.base).
Find the plugin cache at: ~/.claude/plugins/cache/mstack/dev/*/templates/
PLUGIN_DIR=$(ls -d ~/.claude/plugins/cache/mstack/dev/*/templates/ 2>/dev/null | head -1)
if [[ -n "$PLUGIN_DIR" ]]; then
cp "$PLUGIN_DIR"/{design,impl-plan,experiment,cutover-plan,analysis,report,postmortem,kb,ops-guide,playbook}.md docs/templates/
cp "$PLUGIN_DIR/dashboard.base" docs/templates/dashboard.base
cp "$PLUGIN_DIR/dashboard.md" docs/dashboard.md
else
echo "Plugin cache not found. Copy templates manually."
fi
3. Configure Obsidian
If docs/.obsidian/ exists, update docs/.obsidian/app.json to include:
{
"templateFolder": "templates"
}
If docs/.obsidian/ doesn't exist, create it:
mkdir -p docs/.obsidian
echo '{"templateFolder": "templates"}' > docs/.obsidian/app.json
Ensure the Templates core plugin is enabled in docs/.obsidian/core-plugins.json.
4. Update CLAUDE.md
Read the workflow section template from:
TMPL_DIR=$(ls -d ~/.claude/plugins/cache/mstack/dev/*/templates/ 2>/dev/null | head -1)
Append the contents of $TMPL_DIR/claude-md-workflow-section.md to the project's CLAUDE.md.
If CLAUDE.md doesn't exist, create it with just the workflow section.
5. Commit
git add docs/ CLAUDE.md
git commit -m "feat: set up doc-conventions (templates, dashboard, workflow)"
6. Verify
- Run
ls docs/templates/— should show 10 template files + dashboard.base - Run
cat docs/dashboard.md— should show Obsidian transclusion links to dashboard.base views - Run
cat docs/templates/dashboard.base— should show Obsidian Bases view definitions - Open docs/ in Obsidian — dashboard.md should render with tabbed views, templates should be available
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.
- 2d ago First seen · 78 lines · 74 tokens per session scan A 4079dfa78c50
setup-doc-conventions is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 8d ago), licensed MIT. It adds 74 tokens to every session and 720 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…