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/washingtonwei/project-pulse/implementgit clone --depth 1 https://github.com/Washingtonwei/project-pulseWhat 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 | $0.00027 | $0.02563 |
| Opus 5 | $0.00014 | $0.01282 |
| Sonnet 5 | $0.00005 | $0.00513 |
| Haiku 4.5 | $0.00003 | $0.00256 |
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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement — Implement a use case from its design
Take the use case named in $ARGUMENTS (e.g. UC-DOC-create-use-case) and drive it from its design-of-record to working, tested code. This is the second of the two build stages: /design <UC-ID> produces the Level-2 design doc under docs/design/; /implement implements it. The use case is the contract; the linked FRs are the acceptance criteria; the glossary fixes the vocabulary; the design doc is the how you implement.
Precondition — the design must exist. This command builds from an approved design; it does not invent one. Before planning, confirm the area's design doc (docs/design/<area>.md) exists and covers this use case (the 📐 Designed Build state in docs/traceability.md, or a Realizes: header listing this UC-). If there is no design for this use case, stop and tell the developer to run /design <UC-ID> first (or offer to switch to designing it) — don't design-on-the-fly inside the code stage.
The spec and the design are authoritative but not infallible — challenge them. As you drive the design into code, you will hit ambiguous or underspecified steps, assumptions that don't survive contact with the existing code, requirements or design choices that contradict each other or reality, and — because the docs are written by humans and age — unnecessary or incorrect constraints, out-of-date information, wrong assumptions, or an approach that simply isn't best practice or the most efficient one. When that happens, ask the developer a clarifying question or push back — do not silently comply, do not silently invent the missing detail, and do not inherit a constraint just because it's written down. Name the gap or the better way, say what you'd do and why; when it's a genuine spec defect propose the doc edit (per docs/CLAUDE.md, then /spec-build), and when it's a design defect update design/<area>.md (per docs/design/README.md). A step with no backing FR, or a cited FR that doesn't exist, is a question to raise — not something to paper over. When in doubt, or when you see a better way, shout — this holds in every phase.
If no UC-ID is given, ask which use case to implement (or list candidate use cases whose Build state is 📐 Designed in docs/traceability.md — designed and ready to build).
Work in phases. The design was already reviewed and approved in /design, so /implement runs straight through to code — there is no second approval gate. The one thing that still stops you is trouble: if the design contradicts the spec or the existing code, or a decision neither settles, pause and raise it (see the "challenge them" principle above) rather than guessing.
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 · 68 lines · 27 tokens per session scan A a59e2dd31624
implement is a command published in the GitHub repository Washingtonwei/project-pulse (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 2,563 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.