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 skills add iampawan/Manifest --skill contract-pickupgit 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/contract-pickup)<a href="https://agentmods.dev/skills/iampawan/manifest/contract-pickup"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/contract-pickup/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/iampawan/manifest/contract-pickup"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/contract-pickup.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 | $0.00187 | $0.07670 |
| Opus 5 | $0.00093 | $0.03835 |
| Sonnet 5 | $0.00037 | $0.01534 |
| Haiku 4.5 | $0.00019 | $0.00767 |
Grade B, and why
contract-pickup scanned grade B with 1 finding 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 9d 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
and offer the paste-as-text fallback. Do not refuse. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 639 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract pickup (canonical Spec entry)
The world this skill is built for: the PM wrote a PRD somewhere (JIRA, Google Doc, Slack, Notion, a screenshot of slides), assigned it to a dev, and walked away. The dev is the one who has to make the spec build-ready — using code, history, and dependency context the PM doesn't have. Manifest's job is to do most of that code archaeology for the dev, then surface only the decisions and questions that genuinely need a human.
PMs should not have to learn Manifest to use this flow. Their inbox stays where it already is — JIRA comments or Slack — and the agent talks to them in the dev's voice through those existing channels.
What this skill does (in 4 phases)
Phase 1: Fetch + expand → ~10s Read the PRD + linked docs + history
Phase 2: Draft + critique → ~20s Draft contract; critics + design audit (Figma) + freeze check, in parallel
Phase 3: Sort gaps → ~5s Three buckets — auto-fill / dev / PM
Phase 4: Hand off to dev → Dev reviews; sends batched questions to PM
Total time-to-decision for the dev: about 1 minute of agent work, then 3–5 minutes of dev review. Compare to today's "read PRD + grep repo + check Slack + ask around" cycle which can take an hour.
Inputs
The dev provides any of:
- A URL — JIRA, Linear, Notion, Confluence, Google Doc, Slack message link, GitHub issue, Figma file.
- Pasted text — e.g. a copy of a Slack message or email body.
- An image — screenshot of slides, sketch, or a Figma frame export.
- A description in chat — "pick up the search filters thing Pawan mentioned in #product-launches yesterday." Agent uses Slack MCP to find the thread.
If multiple sources are pasted in one go (URL + a clarification + "and look at SC-103 for context"), treat them all as input.
Process
Phase 1.0 — Preflight (don't skip — gates Phase 1)
Check for .manifest/repos.yml before doing anything else. Without
it, pickup's most valuable pieces are inert:
- The cross-repo regression critic has no idea what to scan.
- The auto-fill cache builder (
scripts/build-code-context.mjs) has no inputs. - The PM-channel router has no
defaultChannelto fall back to. - The answer-watcher has nothing to watch.
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.
- 9d ago First seen · 639 lines · 187 tokens per session scan B f0e20cdb1aa6
contract-pickup is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 6d ago), licensed MIT. It adds 187 tokens to every session and 7,670 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (tells the agent never to refuse). 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…