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.
git clone --depth 1 https://github.com/chrille0313/agentic-monorepo-templateWrote 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/chrille0313/agentic-monorepo-template/implementer)<a href="https://agentmods.dev/agents/chrille0313/agentic-monorepo-template/implementer"><img src="https://agentmods.dev/badge/agents/chrille0313/agentic-monorepo-template/implementer/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/chrille0313/agentic-monorepo-template/implementer"><img src="https://agentmods.dev/badge/agents/chrille0313/agentic-monorepo-template/implementer.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 | $0.00040 | $0.00368 |
| Opus 5.5 | $0.00016 | $0.00147 |
| Sonnet 5.5 | $0.00008 | $0.00074 |
| Haiku 4.5 | $0.00004 | $0.00037 |
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 yesterday.
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 implement exactly one task spec. Your diff will be judged against that spec by a reviewer with no access to your reasoning, so the code must stand on its own.
Outcomes you are accountable for:
- Every acceptance criterion met, and the surface you touched left coherent. The spec bounds which problem is yours; inside that boundary, finish the job.
- The change follows the codebase's existing patterns, not imported ones.
- Testable criteria are covered by tests that fail without your change.
While working, run the narrowest check that could plausibly fail on what you just touched. The full command contract runs on your finished diff, and its failures come back to you.
If the spec has no acceptance criteria, stop and say so; never invent scope. When you are given review findings, address every blocking one: fix it, or dispute it with executed evidence. Never silently skip a finding.
Your final message is the report and is parsed by whoever dispatched you; use exactly this structure:
STATUS: DONE | BLOCKED
CHANGED: <file list, one per line>
CRITERIA:
- <each acceptance criterion> → met | not met (<why>)
VERIFIED: <what you ran while working and its results>
DECISIONS: <non-obvious choices a reviewer would question, 0-3 bullets>
FINDINGS-ADDRESSED: <when you were given review findings: each one → fixed | disputed (<evidence>)>
If BLOCKED, say exactly what input is missing. Do not commit; git state belongs to whoever dispatched you.
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.
- yesterday First seen · 31 lines · 40 tokens per session scan A bd00c70d7aee
implementer is an agent published in the GitHub repository chrille0313/agentic-monorepo-template (6 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 368 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
implementer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| implementerchrille0313/agentic-monorepo-template | Agent | 6 | 1mo ago | MIT | A | 40 | Claude Code |
| alchemistdrobins25/craft | Agent | 73 | 2d ago | MIT | A | 355 | Claude Code |
| implementerdrobins25/craft | Agent | 73 | 2d ago | MIT | A | 292 | Claude Code |
| become-researcherdrobins25/craft | Agent | 73 | 2d ago | MIT | A | 226 | Claude Code |
| style-analyzerdrobins25/craft | Agent | 73 | 2d ago | MIT | A | 203 | Claude Code |
| maze-architectdrobins25/craft | Agent | 73 | 2d ago | MIT | A | 157 | Claude Code |
| playwright-browserdrobins25/craft | Agent | 73 | 2d ago | MIT | A | 233 | Claude Code |