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/joanseg/specmanager/specmanager-prdgit clone --depth 1 https://github.com/joanseg/specmanagerWhat 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 | $0.00540 |
| Opus 5 | $0.00014 | $0.00270 |
| Sonnet 5 | $0.00005 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
specmanager-prd 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 2d 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
Draft a PRD for: $ARGUMENTS.
This is the entry point for a new feature. The argument is normally a short feature title (e.g. "Checkout corridor"). If the argument already matches an existing feature, the PRD is drafted for that feature instead.
Steps
- Resolve or create the feature. Call
list_features.- If a feature's
idorslugmatches the argument, use it. - Otherwise treat the argument as a new feature title and call
create_feature({ title }). It generates a kebab-case slug, scaffolds the per-stage folders, writesfeature.json, and refreshesmanifest.json. Report the newid,slug, and folder path. - If no argument was given, ask the user for one short title and stop.
- If a feature's
- Check for an existing draft. Call
list_documents({ featureId, stage: "prd" }). Ignore docs withkind: "interview"— an interview is pre-PRD material, not a PRD; an interview-first flow must not be reported as "a PRD already exists". If a non-interview PRD already exists, ask whether to (a) iterate on it via the panel UI or (b) start over (the user must delete it manually). Do not create a duplicate. - Invoke the subagent. Use the
Tasktool withsubagent_type: "prd-writer"and a prompt that includes:- The feature id and title.
- Any extra context the user gave alongside the slash command.
- Sync CLAUDE.md. When the subagent reports success, call
sync_claude_mdso the managed block reflects the new feature and draft. - Report. Tell the user the new document id and file path. Suggest opening
it in the board (
/specmanager-board) to review, then approve.
Don't
- Don't approve the PRD — only the user does that.
- Don't approve the new feature; features start in
draft. - Don't write the PRD inline in this conversation. Always go through the subagent so the system prompt + tool boundaries apply.
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.
- 2d ago First seen · 42 lines · 27 tokens per session scan A 69b28e719c7a
specmanager-prd is a command published in the GitHub repository joanseg/specmanager (19 stars, last pushed 18d ago), licensed MIT. It adds 27 tokens to every session and 540 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 2026-08-30.
Other commands, from other repositories
version
Display current guide and Claude Code versions.
go-review
Go code review for idiomatic patterns.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.
devs-team
Parallel multi-lens critique of a solution design (the active spec if present, else the decision brief). Dispatches 5 engineering lenses, merges findings, reports a verdict. Report-only, never blocks.
docs-review
Phase 4 of documenting-projects: Quality gate with 8 measurable criteria and iteration. Triggers: '/docs-review', invoked by documenting-projects orchestrator.