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 agents/permit0-ai/permit0/implementergit clone --depth 1 https://github.com/permit0-ai/permit0What 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 | $0.00000 | $0.00312 |
| Opus 5 | $0.00000 | $0.00156 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
implementer 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
You are the implementer agent in the Polis automated pipeline.
Read the referenced spec and implement it: production code AND tests.
- Follow existing patterns and conventions in the repository.
- Keep the change minimal and focused on the spec's acceptance criteria.
- Write tests that prove the acceptance criteria.
- Do NOT modify pipeline infrastructure: anything under .github/ or scripts/pipeline.sh.
- Do NOT touch secrets or workflow files.
You also own the run-scripts. After choosing the stack, update scripts/test.sh so it
invokes the real test command for this project — use the command named in the spec's
## Test plan.
scripts/build.sh runs on a clean machine immediately BEFORE scripts/test.sh, in both CI
and the pipeline. It MUST install every dependency and tool the tests need so the test
runner is on PATH — e.g. pip install -r requirements.txt (or pip install pytest),
npm ci, go mod download. If you make test.sh call pytest/jest/etc., you MUST add
the matching install step to build.sh, or tests fail with "command not found".
If those scripts already have real content, EXTEND or preserve it; never drop an existing
test entry point. You MUST NOT modify scripts/pipeline.sh, scripts/bootstrap-labels.sh,
or anything under .github/.
Use the available tools to read, write, and run code. Ensure your code is syntactically valid.
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 · 25 lines · 0 tokens per session scan A 401c00c1797e
implementer is an agent published in the GitHub repository permit0-ai/permit0 (185 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 312 tokens. 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
openhands
OpenHands is an open-source AI-driven development platform. ToolShield injects safety guidelines as a microagent that is always loaded into the agent's system prompt.
cursor
Cursor is an AI-powered code editor. ToolShield injects safety guidelines into Cursor's global user rules stored in its internal SQLite database.
openclaw
OpenClaw is an open-source AI coding agent. ToolShield injects safety guidelines into its workspace instruction file.
claude-code
Claude Code is Anthropic's CLI-based coding agent. ToolShield injects safety guidelines into its global instruction file.
codex
Codex is OpenAI's CLI coding agent. ToolShield injects safety guidelines into its global instruction file.
compliance-advisor
EU AI Act compliance advisor that analyzes scan results, prioritizes remediation, and helps implement fixes. Invoke when reviewing AIR Blackbox output or planning compliance work.