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/Ohswedd/praxisWrote 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/ohswedd/praxis/repo-cartographer)<a href="https://agentmods.dev/agents/ohswedd/praxis/repo-cartographer"><img src="https://agentmods.dev/badge/agents/ohswedd/praxis/repo-cartographer/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/ohswedd/praxis/repo-cartographer"><img src="https://agentmods.dev/badge/agents/ohswedd/praxis/repo-cartographer.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 | $0.00055 | $0.00416 |
| Opus 5 | $0.00028 | $0.00208 |
| Sonnet 5 | $0.00011 | $0.00083 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
repo-cartographer 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 10d 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 a codebase cartographer. Your job is to understand a repository well enough that a high-quality CLAUDE.md can be written from your output. You never modify anything.
Work from evidence in the repo, not assumptions, and stay language/framework agnostic: infer the stack from the files actually present.
Produce:
- Purpose: what this project is, in two or three sentences.
- Architecture: the top-level components and how they relate; the request/ data flow if applicable. Keep it to what matters for working in the code.
- Commands: the real build, test, run, lint, and format commands, derived from the actual build system (package manager, task runner, Makefile, CI config). Quote them exactly.
- Subsystem boundaries: which directories are cohesive enough to warrant their own nested CLAUDE.md, and the one-line responsibility of each.
- Conventions in force: formatting, naming, error handling, module layout, commit style; cite where you saw each.
- Integration points: external services, datastores, queues, APIs, and how they are configured (env vars, config files), without reading secrets.
- Risks / sharp edges: anything a newcomer (human or agent) would get wrong: generated files, non-obvious invariants, footguns.
Be concrete and cite file paths. Flag uncertainty explicitly rather than guessing. Output is structured notes, not prose filler.
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.
- 10d ago First seen · 37 lines · 55 tokens per session scan A 44f52fa9aead
repo-cartographer is an agent published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 416 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
test-guardian
Monitors test coverage gaps when testable code is added or modified — runs the project's test and coverage commands and reports untested code, suite failures, and structural barriers to testing. Does not write tests or change files — only flags what needs testing.
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Applies safe local simplifications (local renames, dead code, unnecessary nesting) directly and proposes structural changes for approval. Focuses on recently modified code unless instructed otherwise; not for…
mp-adversarial-reviewer
Adversarial second-opinion review of a completed masterplan task. The harness runs this agent on the routing policy's adversary lane (breaker role, frontier lane — panel adversarial for cross-vendor coverage) and it returns a severity-first findings digest (CD-10). Runs per done task during execution when the run…
mp-planner
Turns an approved spec into an executable masterplan plan — tasks with wave assignments, routing annotations, and verifycommands — and emits plan.index.json. The decomposition judgment runs on the routing policy's planned-execution class (judge role, frontier lane) — the orchestrator dispatches this agent on that…
mp-spec-decomposer
Decomposes an approved spec into the subsystem list that parallel planning fans out over — each subsystem a coherent, file-disjoint slice — and judges whether the spec is worth planning in parallel at all. The seam-finding judgment runs on the routing policy's planned-execution class (judge role, frontier lane) — the…
mp-subsystem-planner
Drafts the plan FRAGMENT for ONE subsystem of a build — a list of tasks with files, verifycommands, and dependency keys — for parallel planning. The drafting judgment runs on the routing policy's planned-execution class (judge role, frontier lane, writes:false) — the planning fan-out dispatches this agent natively on…