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 instructions/joanseg/specmanager/claude-mdgit 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 | $0.03275 | $0.03275 |
| Opus 5 | $0.01638 | $0.01638 |
| Sonnet 5 | $0.00655 | $0.00655 |
| Haiku 4.5 | $0.00328 | $0.00328 |
Grade A, and why
specmanager CLAUDE.md 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project lifecycle (managed by SpecManager — do not edit by hand)
Specs live in .claude/specs/features/. Read the approved doc for a feature's stage before implementing it.
| Feature | Current stage | Notes |
|---|---|---|
| Redesign | PRD (approved) | — |
| Dummy feature | PRD | — |
| Post-phase design conformance check | PRD (draft) | — |
| Markdown viewer | PRD (approved) | — |
| Reinstall refactor | PRD (approved) | — |
| Interview command | PRD (approved) | — |
| Antigravity plugin | PRD (approved) | — |
| Share docs on public URL | PRD (approved) | — |
| Cursor plugin | PRD (approved) | — |
| Codex plugin | PRD (approved) | — |
| User adoption acceleration | PRD (draft) | — |
| Token usage optimisation | PRD (approved) | — |
| Viral loop feature | PRD (approved) | — |
| Feature demo recording | PRD | — |
| Spec-stage tier dispatch | PRD (approved) | — |
| GitHub spec sync (issues/PRs) | PRD | — |
| Security review stage | PRD (approved) | — |
| Multi-repo nested docs (CLAUDE.md / DESIGN.md) | PRD (draft) | — |
| Multi-session boards (auto-port) | PRD (approved) | — |
| Website agent readiness | PRD | — |
8 features shipped — full history on the board.
Rules: don't start a feature's tasks until its Plan is approved; treat ⚠️ stale docs as needing reconciliation.
Commands:
/specmanager-prd · /specmanager-architecture · /specmanager-design (optional) · /specmanager-plan · /specmanager-build · /specmanager-walkthrough · /specmanager-board · /specmanager-interview (optional, pre-PRD)
Last synced: 2026-07-10T12:08:11.497Z
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
This repo is the SpecManager plugin (implemented, not a spec). SpecManager is a Claude Code plugin that turns a project's lifecycle (PRD → Architecture → optional Design → Plan + tasks → Build → Walkthroughs) into a localhost kanban board backed by plain markdown in the target project's repo. Single-user, fully local, bound to 127.0.0.1, no auth. Claude drafts each stage from the previous approved one plus the existing codebase; the human edits and approves in the board; git tracks every artifact.
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 · 132 lines · 3,275 tokens per session scan A 820a17430233
specmanager CLAUDE.md is an instructions file published in the GitHub repository joanseg/specmanager (19 stars, last pushed 19d ago), licensed MIT. It adds 3,275 tokens to every session, about $0.0164 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 instructions, from other repositories
spec-superflow AGENTS.md
Instructions for MageByte-Zero/spec-superflow, covering agents.md, what this is, commands, build typescript and run integration tests.
spec-superflow GEMINI.md
Instructions for MageByte-Zero/spec-superflow, covering spec-superflow and spec-superflow v1.0.1 | 阶段: {{state}} | 工作流: {{workflow}}.
spec-superflow copilot-instructions.md
Instructions for MageByte-Zero/spec-superflow, covering phase guard, ✅ 允许操作, ⛔ 禁止操作 and 🔔 决策点.
spec-manager CLAUDE.md
Instructions for loki-ai-ch/spec-manager, covering claude.md, spec-driven development — no vibe coding, build & test commands, architecture and source layout.
spec-manager AGENTS.md
Instructions for loki-ai-ch/spec-manager, covering spec-manager workflow capsule, mandatory workflow and common commands.
Plans CLAUDE.md
Instructions for yrangana/Plans, covering claude.md, plans repo, what this repo is, repo structure, site deployment and style rules.