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-checknpx skills add iampawan/Manifest --skill setup-checkgit clone --depth 1 https://github.com/iampawan/ManifestWrote 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/iampawan/manifest/setup-check)<a href="https://agentmods.dev/skills/iampawan/manifest/setup-check"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/setup-check.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01915 |
| Opus 5 | $0.00036 | $0.00958 |
| Sonnet 5 | $0.00015 | $0.00383 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
setup-check 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup check
Your job is to make Manifest self-explanatory at runtime. The user shouldn't have to read three docs to know what's missing — they should run one command and see exactly what's wired, what's not, and what to do about each.
When you run
Triggered by any of:
- User invokes
/manifest setupor/setup - User invokes
/manifestfor the first time (no.manifest/directory in the current working dir) - Another skill detects a missing required MCP and routes here ("you need the Atlassian MCP for that — let me check your setup")
Process
1. Discover what's connected
Try to list the user's connected MCPs. Two paths:
Preferred — use the MCP registry tool if available:
mcp__mcp-registry__list_connectors()
This returns the connectors the user has installed. Cross-reference against Manifest's MCP requirements below.
Fallback — if list_connectors isn't available, probe each
MCP by checking whether its tools appear in the current toolset.
If the user's environment doesn't expose tool listings, fall
back to asking the user: "Which of these do you have connected?
[checklist]".
2. Cross-reference against Manifest's requirements
| MCP | Tier | What Manifest uses it for |
|---|---|---|
| GitHub | Required | Read code across repos, open PRs, post comments. Required for regression critic (multi-repo scanning) and the Implementer. |
| Sentry | Required | Errors, releases, performance per release. Required for verify-deployment, launch-report, bug-triage. |
| Slack | Required | Human gates, daily reports, contract threads. Required for the cycle to be usable in a team setting. |
| Firebase Analytics | Recommended | Richest source for launch-report success metrics. Without it, launch report falls back to server logs / DB / Sentry. |
| Amplitude | Recommended | Alternative client analytics if you use it instead of Firebase. |
| Atlassian (JIRA + Confluence) | Recommended | Pull contracts from JIRA tickets via URL, auto-file bugs, link Confluence pages. Without it, /contract new <jira-url> won't work — falls back to free-text intake. |
| Figma | Optional | Implementer reads design frames; comms-completeness critic verifies UI state coverage. Without it, design alignment is human-only. |
| Google Cloud Logging / Datadog / Loki | Optional | Server-side event count fallback when no client analytics. |
| Postgres / DB MCP | Optional | Direct record-count fallback for launch metrics. |
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 First seen · 202 lines · 73 tokens per session scan A a0d1ebbbdb99
setup-check is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,915 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…