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-decomposegit 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-decompose)<a href="https://agentmods.dev/skills/iampawan/manifest/contract-decompose"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/contract-decompose.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 5.1 | $0.00079 | $0.02028 |
| Opus 5 | $0.00039 | $0.01014 |
| Sonnet 5 | $0.00016 | $0.00406 |
| Haiku 4.5 | $0.00008 | $0.00203 |
Grade A, and why
contract-decompose 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 7d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract decomposer (smart Large support)
A Large contract shouldn't be agent-shipped on a 24/72h timer — but it shouldn't be thrown over the wall either. Your job: break it into a sequence of independently-shippable Small/Medium child contracts, ordered by dependency, so a multi-week epic becomes a series of 24h/72h pieces. The Large contract stays as the epic that owns the overall success metric and tracks aggregate progress.
When this runs
- A contract was sized
largeby the validator, and the user wants to proceed (rather than abandon). - Invoked via
/contract decompose <ID>or routed here from/contract promotewhen it detects a Large contract.
Process
1. Read the Large contract
Read .manifest/contracts/<ID>.md. Confirm complexity: large.
Pull the goal, success metrics, all behaviors, and the critic findings
(the critics still ran on the Large spec — use their edge cases and
regression notes to inform the split).
2. Find the natural seams
Decompose along the lines that make each piece independently shippable and valuable. Good seams, in rough priority:
- Platform: ship web first, then iOS, then Android (each a child).
- Behavior cluster: group behaviors that share a surface or data model into one child; split unrelated ones.
- Risk isolation: pull migrations, auth/billing changes, and new infrastructure into their OWN children, flagged human-led (see §4).
- Enablement → feature: a child that adds the backend endpoint (behind a flag, no UI) before the child that adds the UI consuming it. The first ships safely with nothing user-visible.
- Read before write: ship the read/display path before the mutation path when that lets you validate data independently.
Each child should be Small or Medium on its own. If a proposed child is still Large, recurse — decompose it further.
3. Order by dependency
Build a DAG: which children must ship before which. A child that consumes an API can't ship before the child that adds the API (unless flag-gated to be inert). Produce a linear order that respects the DAG, with parallelizable children noted.
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.
- 7d ago First seen · 182 lines · 79 tokens per session scan A 600cffab1bd3
contract-decompose is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 2,028 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.