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-initgit 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 | $0.00025 | $0.00871 |
| Opus 5 | $0.00013 | $0.00436 |
| Sonnet 5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
specmanager-init 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize this project for SpecManager.
What this does
- Creates
.claude/specs/(andfeatures/) if missing. - Writes/refreshes
manifest.json(the rebuildable board index). - Writes a managed block into the project's
CLAUDE.mdbetween<!-- specmanager:start -->and<!-- specmanager:end -->. Content outside those markers is never touched. IfCLAUDE.mddoes not exist it is created with just the managed block. - Creates or refreshes
./docs/DESIGN.md— the repo-level design-system spec, following the Google Stitch DESIGN.md spec. Tokens (colors, typography, spacing, components) are inferred from the existing UI source files (CSS custom properties, sample component files, Tailwind config). The managed region lives between<!-- specmanager:design:start -->/<!-- specmanager:design:end -->; anything outside is the user's territory. Re-runs are idempotent and non-destructive.
Steps
- Call the
specmanager_initMCP tool first (idempotent — safe to re-run). This creates.claude/specs/+manifest.json, writes the managed CLAUDE.md block between the<!-- specmanager:start -->/<!-- specmanager:end -->markers, and creates/refreshes./docs/DESIGN.md. - After it returns, run the native
/initslash command in-session to populate CLAUDE.md's general codebase-doc region./initis a native interactive command the agent runs in-session — it is not a server/MCP call. It writes only outside the SpecManager markers, so it never clobbers the managed block (the marker-merge incore/claude-md.tsis line-anchored, so the regions are disjoint). Runningspecmanager_initfirst means the markers already exist when/initfills the surrounding codebase docs. - Report what changed across both regions:
- From
specmanager_init: which directories were created, whether the managed CLAUDE.md block was created/updated, and whether./docs/DESIGN.mdwas created/updated. - From
/init: that the general codebase docs in CLAUDE.md (outside the markers) were (re)generated — so the user need not run/initseparately.
- From
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 · 65 lines · 25 tokens per session scan A 82749749fd31
specmanager-init is a command published in the GitHub repository joanseg/specmanager (19 stars, last pushed 18d ago), licensed MIT. It adds 25 tokens to every session and 871 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.