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 commands/iampawan/manifest/implementgit 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 | $0.00025 | $0.00526 |
| Opus 5 | $0.00013 | $0.00263 |
| Sonnet 5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
implement 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 yesterday.
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.
What it actually says
/implement
Triggers the implement skill against the given contract's latest revision.
New here?
Run /manifest tutorial for the 3-minute orientation before invoking
this. The Implementer is the heaviest agent in the system — it
expects a verified, promoted contract and runs for up to 8 hours.
Don't fire it casually.
Usage
/implement <ID>
Where to run it
Both paths invoke the same skill. Pick based on your situation.
Locally — in your Claude Code session (recommended for pilot/MVP)
/implement AUTH-1234
Runs the agent in your current session. You see what it's doing in real time, can intervene if it goes sideways, can pause and resume. Uses your existing Claude Code subscription auth — no separate token needed. Best for:
- Demos and pilots (no CI setup required)
- Small features (1–3 hours of agent work)
- When you want full visibility / control
Caveat: your Claude Code session has to stay open while the agent runs.
From a PR comment — via the pr-verify.yml workflow (recommended for team-scale use)
Comment on a draft PR:
@claude /implement AUTH-1234
The workflow invokes the claude CLI headlessly in CI. The agent
pushes commits to the PR branch. Uses a CLAUDE_CODE_OAUTH_TOKEN
or ANTHROPIC_API_KEY secret. Best for:
- Medium+ features (multi-hour agent runs)
- When the dev wants to close their laptop and walk away
- Team-wide use where many devs trigger implementations independently
- When you want every Implementer run captured in CI logs
Caveat: needs the workflow file installed in the target repo and a secret provisioned.
Output
- Code changes pushed to the PR branch.
- Playwright tests under
tests/<contract-id>.spec.tstagged with@contract:<ID>and@ac:<ACn>. - AC coverage comment on the PR.
Prerequisites
- Contract must be in
status: promotedand have a revision file. - Complexity must be
smallormedium(Large is refused).
Examples
/implement SC-005
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.
- yesterday First seen · 81 lines · 25 tokens per session scan A 9e55f933650e
implement is a command published in the GitHub repository iampawan/Manifest (5 stars, last pushed 20d ago), licensed MIT. It adds 25 tokens to every session and 526 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.