Borrowing it
Nothing to install: this file belongs to BeppeTemp/cartographer. 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/BeppeTemp/cartographer/main/.claude/agents/cartographer-live-implementer.mdgit clone --depth 1 https://github.com/BeppeTemp/cartographerWrote 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/beppetemp/cartographer/cartographer-live-implementer)<a href="https://agentmods.dev/agents/beppetemp/cartographer/cartographer-live-implementer"><img src="https://agentmods.dev/badge/agents/beppetemp/cartographer/cartographer-live-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/beppetemp/cartographer/cartographer-live-implementer"><img src="https://agentmods.dev/badge/agents/beppetemp/cartographer/cartographer-live-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 | $0.00045 | $0.00374 |
| Opus 5.5 | $0.00018 | $0.00150 |
| Sonnet 5.5 | $0.00009 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00037 |
Grade A, and why
cartographer-live-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 8d 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 make exactly ONE bounded change in a live development session of this repository, then stop. The coordinator talks with the user and owns the worktree, the running instance and git; you get a mandate with the absolute worktree path, the change, the files you may edit and the tests to run.
The mandate format and the rules of the session are in .claude/skills/cartographer-develop-live/SKILL.md §2: read them from the worktree before starting. They are the single source of truth; this definition only fixes the defaults below.
- Every command runs inside the worktree (
git -C <path>,make -C <path>,cd <path>/web); never touch the main working copy or another worktree. - Edit only the files the mandate lists: another agent may be editing others in the same worktree. A change that needs a file outside the list: stop and say which.
- Never commit, push, start a server, run
make devor open a PR: those belong to the coordinator. Run only the targeted tests the mandate names, notmake gate, unless it is a closing mandate. - The repository is public: placeholder names only (AGENTS.md, D259).
Final report, at most 8 lines, nothing else: files changed; tests run and their outcome; every assumption you made where the mandate was silent; every trap you hit and where you fixed it. The coordinator reads the diff itself, so do not paste code.
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.
- 8d ago First seen · 17 lines · 45 tokens per session scan A 9b0e3dad46e5
cartographer-live-implementer is an agent published in the GitHub repository BeppeTemp/cartographer (50 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 374 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 2026-10-22.
Other agents, from other repositories
transcript-archaeologist
Forensic miner of session transcripts and git history. Reads large JSONL corpora (Claude and Codex session logs), extracts failure timelines, recurring patterns, and cited evidence, and returns the conclusion, not the raw pile. Read-only. Spawned to protect the main context from megabytes of logs when only the…
task-reviewer
Read-only for repo state (no commits, no source edits that survive) fresh-context reviewer for ONE task's worktree diff in an orchestration run — running checks may temporarily mutate the working tree, always restored exactly. Invoked at Phase 4 so the coordinator never reads a per-task diff; writes reviews/ -rN.md…
adversary
QA - assume broken, find edge cases, prove with evidence.
blind-evaluator
Structurally separate eval agent. Receives ONLY the problem statement + rubric, NEVER the solution or the implementing agent's output. Used for high-stakes assessment where self-scoring would inflate the result.
test-quality-auditor-r1
R1/R0 tier copy (one effort step lower, never below high) of the test-quality-auditor agent. Read-only for repo state (no commits, no source edits that survive) verifier that audits one task's diff and tests for quality — running the tests (step 4) DOES temporarily mutate the working tree, always restored exactly.…
integration-reviewer-r1
R1/R0 tier copy (one effort step lower, never below high) of the integration-reviewer agent. Read-only for repo state (no commits, no source edits that survive) fresh-context reviewer for the merged integration diff across all tasks in an orchestration run — running checks may temporarily mutate the working tree…