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/iampawan/manifest/setup-initnpx skills add iampawan/Manifest --skill setup-initgit clone --depth 1 https://github.com/iampawan/ManifestWhat 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 | $0.00077 | $0.02719 |
| Opus 5 | $0.00039 | $0.01359 |
| Sonnet 5 | $0.00015 | $0.00544 |
| Haiku 4.5 | $0.00008 | $0.00272 |
Grade A, and why
setup-init 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup wizard
Your job is to produce a COMPLETE, ready-to-use .manifest/repos.yml
with no ⚠️ FILL IN placeholders left. Detect everything you can,
ask only what you can't, confirm, and write. The user should never
have to hand-edit YAML after this.
Detect → ask the minimum → auto-fill → confirm → write.
Step 1 — Discover the repos
Try these in order until you have the repo list:
- Ask the user — "Which repos are part of this product? Paste
GitHub identifiers (
org/repo) or local paths, one per line." Accept either form. This is the primary, universal method. - Scan a workspace dir — if the user points at a parent folder
(e.g.,
~/Documents/dev/<product>), list its subdirectories that are git repos (.gitpresent) and propose them. - GitHub org listing — if the GitHub MCP is connected and the user names their org, list its repos and ask which are in scope.
Do NOT assume any particular code-index or navigator MCP exists. Discovery must work with nothing but the GitHub MCP and the user's input.
Step 2 — Auto-detect each repo's stack (deterministic)
For LOCAL repos, run the bundled deterministic detector — don't eyeball it:
node <plugin-root>/scripts/detect.mjs <repo-path-1> <repo-path-2> ...
It returns JSON per repo: framework, languages, eventSdk,
testFramework, testPattern, and a confidence. This is code, not
a guess — reproducible and fast.
For REMOTE repos (GitHub MCP only, no local clone), fetch the marker
files (package.json, pubspec.yaml, go.mod, build.gradle,
requirements.txt, pyproject.toml, Package.swift, Gemfile) via
get_file_contents and apply the same logic (the detector's
detectFromFiles core, or the STACK-PROFILES table by hand).
The detector reports the same fields described below. Treat anything
it marks confidence: low (framework "unknown") as a question for
Step 4, not a guess. The reference for what each value means:
framework (from marker files)
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 · 241 lines · 77 tokens per session scan A a53d9d1cfe07
setup-init is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 21d ago), licensed MIT. It adds 77 tokens to every session and 2,719 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…