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/rtazima/claude-proj-blueprint/implementgit clone --depth 1 https://github.com/rtazima/claude-proj-blueprintWhat 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 | $0.00000 | $0.00419 |
| Opus 5 | $0.00000 | $0.00210 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
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 3d 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.
What it actually says
Implement a feature from a PRD.
Arguments: $ARGUMENTS (PRD path, e.g. docs/product/feat-auth.md)
Workflow:
- Read the PRD at $ARGUMENTS
- Enter Plan Mode — create a detailed plan before coding
- Check related ADRs in docs/architecture/
- Check applicable specs in docs/specs/
- Detect design flow (in priority order):
- If
docs/design/<prd-slug>-PROMPT.mdexists OR PRD references a Claude Design handoff → activateclaude-design-handoffskill: parse PROMPT.md, reconcile against CLAUDE.md + PRD, produce reconciliation report, resolve conflicts with user, then hand off tofrontend-agent - Else if the PRD contains a Figma link → use Figma MCP to extract design context, then implement
- Else → activate the
frontend-agentskill: a. Load design tokens from docs/specs/design-system/README.md b. Scan existing UI components for consistency c. Generate UI from PRD requirements + tokens + component library
- If
- Implement following CLAUDE.md and the implement-prd skill
- Create tests following the testing skill
- Documentation checklist — before committing, verify and update:
- CLAUDE.md module map (if new files/modules)
- .env.example (if new environment variables)
- README.md project structure (if new files/modules)
- ADR in docs/architecture/ (if architectural decisions were made)
- Gotchas in CLAUDE.md (if new edge cases discovered)
- Notes in the PRD (if implementation revealed business insights)
- Runbook in docs/runbooks/ (if new operational procedures needed) Skip items that don't apply, but actively check each one.
- Commit with Conventional Commits format message
Always ask for plan confirmation before starting implementation.
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.
- 3d ago First seen · 33 lines · 0 tokens per session scan A fea854471ded
implement is a command published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 419 tokens. 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 2026-08-30.
Other commands, from other repositories
sruja-bugfix-triage
Systematic workflow for triaging and fixing bugs with architecture grounding.
sruja-verify-task
Run verification steps for a task profile. Use before marking a task as done.
adr-draft
Draft one new ADR from a current decision or a selected backfill handoff. Writes a single new record, as proposed.
release-check
Pre-release checklist (run before pushing a v tag).
readme-audit
Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.
verify-loop
Run the full local verification loop (check + drift).