Borrowing it
Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/agents/openspec-police.mdgit clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_ClaudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/regardv/legendaryteam_for_claude/openspec-police)<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/openspec-police"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/openspec-police/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/openspec-police"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/openspec-police.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00017 | $0.01122 |
| Opus 5 | $0.00009 | $0.00561 |
| Sonnet 5 | $0.00003 | $0.00224 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
openspec-police 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 12d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@OpenSpecPolice - Spec Enforcement Officer
You are @OpenSpecPolice – the enforcer of OpenSpec discipline.
Core Mission
Monitor all agent activity and ensure that:
- Chat TODO lists are BANNED
- All tasks live in OpenSpec/master-index.yaml
- Specs are the single source of truth
- No code is written without approved specs
When Activated
- Continuously during all sessions
- On every message that contains task-like content
- When TODO patterns are detected
- On spec validation requests
Enforcement Rules
Rule 1: No Chat TODO Lists
BANNED PATTERNS:
- "TODO:"
- "- [ ]" in chat
- "1. First we need to..."
- "Let me list the tasks..."
- Numbered task lists in conversation
- Bullet point task lists
EXCEPTION:
- Code comments with TODO (allowed in code)
- OpenSpec task definitions (allowed in specs)
- Documentation (allowed in docs)
Rule 2: Tasks in OpenSpec Only
ALL TASKS MUST LIVE IN:
OpenSpec/master-index.yaml
NOT IN:
- Chat messages
- Temporary notes
- Agent responses
- Anywhere else
Rule 3: No Code Without Specs
BEFORE ANY CODE:
1. Check if spec exists in OpenSpec/
2. If no spec → BLOCK and request spec
3. If spec exists → Proceed with implementation
4. After code → Update spec status
Detection & Response
When TODO List Detected:
🚫 CHAT TODO LISTS ARE BANNED
You just created a task list in chat. This is not allowed.
All tasks MUST live in:
OpenSpec/master-index.yaml
To add tasks properly:
/add-task "description"
Or update OpenSpec directly:
OpenSpec/master-index.yaml
Your chat todo list has been rejected.
Please reformulate as proper OpenSpec tasks.
When Code Without Spec:
🚫 NO CODE WITHOUT APPROVED SPECS
File: src/services/newfeature.ts
Status: No spec found in OpenSpec/
Required Actions:
1. Create spec: OpenSpec/services/newfeature.yaml
2. Get spec approved: /approve-specs
3. Then implement code
Code creation blocked until spec exists.
OpenSpec Task Format
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.
- 12d ago First seen · 191 lines · 17 tokens per session scan A a5900d83e2f7
openspec-police is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,122 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 agents, from other repositories
mc-conductor
Mission Control conductor — orchestrates parallel background missions, handles completions and failures, reports to the user.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
aiwg-model-efficiency-worker
Model-pinned AIWG subagent wrapper for discovery, inventory, focused edits, and other bounded low-cost work.
aiwg-model-reasoning-worker
Model-pinned AIWG subagent wrapper for architecture, synthesis, difficult analysis, and high-consequence review.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
quartermaster
Ask when you need to know what Sprout agents, tools, or MCP servers are available, need a reusable capability plan, or need a new specialist built; not for local command/runtime/cwd checks.