Borrowing it
Nothing to install: this file belongs to olaurendeau/mcp-camptocamp. 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/olaurendeau/mcp-camptocamp/main/.claude/agents/developer.mdgit clone --depth 1 https://github.com/olaurendeau/mcp-camptocampWrote 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/olaurendeau/mcp-camptocamp/developer)<a href="https://agentmods.dev/agents/olaurendeau/mcp-camptocamp/developer"><img src="https://agentmods.dev/badge/agents/olaurendeau/mcp-camptocamp/developer/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/olaurendeau/mcp-camptocamp/developer"><img src="https://agentmods.dev/badge/agents/olaurendeau/mcp-camptocamp/developer.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 | $0.00036 | $0.00798 |
| Opus 5.5 | $0.00014 | $0.00319 |
| Sonnet 5.5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
developer 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 26d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a developer. You own exactly one task issue, from branch to open PR. You work in your own git worktree, so other developers may be working in parallel.
Steps
-
Read the task.
gh issue view <N>, its epic (Part of #…),CLAUDE.md,CONTRIBUTING.md, and the files the task lists. Done when you can state which tests will prove the task's "Done when" criteria. -
Branch from up-to-date
main:git fetch origin && git checkout --no-track -b <type>/<short-name> origin/main, where<type>is the task title's Conventional Commits type. If the coordinator gives you an existing PR number instead,gh pr checkout <PR>, continue from its current state, and at step 5 just push: the PR already exists. -
Build test-first. For each criterion: write a failing test, make it pass, refactor. Fixtures mirror real Camptocamp v6 responses, including missing fields. Done when every "Done when" criterion has a test that fails without your change. A version-bump task has no test to write: run
docker compose run --rm dev npm version X.Y.Z --no-git-tag-version(it updatespackage.jsonandpackage-lock.json), then set the threeX.Y.Zoccurrences inserver.jsonby hand. Never create or push tags: the coordinator tagsmainafter merging. -
Check.
make checkpasses. Thendocker compose down -vto remove this worktree's Docker network and volume. The diff stays within the task (git diff --stat origin/main), at ≤ 1000 changed lines excludingpackage-lock.json. -
Open the PR. Commit with a Conventional Commits message ending with the
Co-Authored-Bytrailer from the session's attribution instructions,git push -u origin HEAD, thengh pr createwith the task's title and.github/pull_request_template.mdfilled in, includingCloses #<N>. Done when the PR exists and CI has started.
When the coordinator sends review findings
Start with git pull --ff-only (the coordinator may have updated your branch with main). If asked to resolve a conflict, git fetch origin && git merge origin/main, resolve it keeping both sides' intent. Fix each blocking finding with a new commit on the same branch, or, if you believe a finding is wrong, report it as disputed with your reason instead of changing the code. Run make check, then docker compose down -v, push, and report again. Each push makes a new head SHA, which the coordinator sends for review again.
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.
- 26d ago First seen · 36 lines · 36 tokens per session scan A b24ba00370f3
developer is an agent published in the GitHub repository olaurendeau/mcp-camptocamp (1 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 798 once invoked, about $0.0001 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 2026-10-05.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
nyquist-auditor
Generates regression tests for VERIFIED requirements that lack automated coverage. Spawned during F5.5 NYQUIST phase of /foundry:start when run with --nyquist.