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-interviewgit 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 | $0.00042 | $0.01658 |
| Opus 5 | $0.00021 | $0.00829 |
| Sonnet 5 | $0.00008 | $0.00332 |
| Haiku 4.5 | $0.00004 | $0.00166 |
Grade A, and why
specmanager-interview 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview the user about: $ARGUMENTS.
Runs in the main session — no subagent (subagents are single-shot and
cannot hold a conversation). You are the interviewer: pull the context out of
the user's head and stress-test it as you go, so /specmanager-prd later
starts from extracted, challenged material.
Steps
-
Resolve or create the feature.
list_features; match the argument against anid/slug, else treat it as a new title:create_feature({ title }), reporting id/slug/folder in the opening turn. No argument → ask for one short title and stop. -
Detect prior material.
list_documents({ featureId, stage: "prd" }). Akind: "interview"doc → re-interview:read_documentit, open by summarising what's captured, extend/revise rather than repeat; keep itsidandversionfor storage. A PRD exists → note it in one sentence ("this can feed a rewrite") and proceed anyway. -
Interview per the protocol below.
-
Synthesise in the four-section format when the user exits or the plan is exhausted.
-
Storage. Ask:
Store this interview as a markdown file for this feature? It will appear in the PRD column on the board. (yes / no)
Stored body = one-line mode note (mode(s) ran + method credit), then the four sections — chat and artifact match. Then:
- No → stop; nothing is written.
- Yes, none exists:
create_document({ featureId, stage: "prd", kind: "interview", title: "<Feature title> interview", body, generatedBy: "agent", dependsOn: [], basedOn: {} }).dependsOn: []/basedOn: {}is a hard contract — the interview sits outside the staleness graph; never link it. Filename defaults toprd/interview.md. - Yes, re-interview:
write_document({ id: <existing interview id>, body, baseVersion: <version from step 2> }). Onversion conflict,read_documentagain, merge, retry with the fresh version.
On success:
sync_claude_md, then report the document id and file path.
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 · 136 lines · 42 tokens per session scan A 2d18b704f6f4
specmanager-interview is a command published in the GitHub repository joanseg/specmanager (19 stars, last pushed 18d ago), licensed MIT. It adds 42 tokens to every session and 1,658 once invoked, about $0.0002 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.