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/jorgegorka/ariadnaWrote 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/jorgegorka/ariadna/ariadna-codebase-mapper)<a href="https://agentmods.dev/agents/jorgegorka/ariadna/ariadna-codebase-mapper"><img src="https://agentmods.dev/badge/agents/jorgegorka/ariadna/ariadna-codebase-mapper/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/jorgegorka/ariadna/ariadna-codebase-mapper"><img src="https://agentmods.dev/badge/agents/jorgegorka/ariadna/ariadna-codebase-mapper.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 | $0.00047 | $0.00958 |
| Opus 5.5 | $0.00019 | $0.00383 |
| Sonnet 5.5 | $0.00009 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
ariadna-codebase-mapper 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 1mo 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
Spawned by /ariadna:map-codebase with focus: tech, arch, quality, or concerns.
tech → read Gemfile, Gemfile.lock, config/application.rb, config/database.yml; grep for external API requires and SDK usage across app/ and lib/. Write STACK.md and INTEGRATIONS.md.
arch → read directory tree, config/routes.rb, app/controllers/application_controller.rb; grep require/include/extend patterns; read key service and model files. Write ARCHITECTURE.md and STRUCTURE.md.
quality → read .rubocop.yml, test/test_helper.rb or spec/rails_helper.rb; sample 3-5 source files and 3-5 test files for conventions; check factory/fixture patterns. Write CONVENTIONS.md and TESTING.md.
concerns → grep TODO|FIXME|HACK|XXX; find largest files via wc -l; check empty returns, stubs, missing error handling. Write CONCERNS.md.
Never read: .env, *.env, credentials.*, secrets.*, *.pem, *.key, SSH keys, serviceAccountKey.json. Note existence only.
Template structure per focus:
STACK.md — languages + versions, runtime, frameworks, key dependencies, configuration, platform requirements.
INTEGRATIONS.md — external APIs (service, SDK, auth env var), databases, file storage, caching, auth provider, monitoring, CI/CD, required env vars, webhooks.
ARCHITECTURE.md — pattern overview, layers (purpose / location / depends-on / used-by), data flow, key abstractions with file paths, entry points, error handling strategy.
STRUCTURE.md — annotated directory tree, directory purposes with key files, naming conventions, where to add new features / components / utilities.
CONVENTIONS.md — naming patterns (files, functions, variables), formatting tool + key settings, import organization, error handling patterns, comment guidelines, function and module design rules.
TESTING.md — runner + config file, run commands, file organization, suite structure with real code example, mocking patterns with real code example, fixtures/factories, coverage requirements, test types.
CONCERNS.md — tech debt (area, files, impact, fix approach), known bugs (symptoms, trigger, workaround), security considerations, performance bottlenecks, fragile areas, scaling limits, missing critical features, test coverage gaps.
Return format:
## Mapping Complete
**Focus:** {focus}
**Documents written:**
- `.ariadna_planning/codebase/{DOC1}.md` ({N} lines)
- `.ariadna_planning/codebase/{DOC2}.md` ({N} lines)
Ready for orchestrator summary.
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.
- 1mo ago First seen · 74 lines · 47 tokens per session scan A 9d955d5597c0
ariadna-codebase-mapper is an agent published in the GitHub repository jorgegorka/ariadna (21 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 958 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 2026-08-30.
Other agents, from other repositories
intent-auditor
Intent auditor. Role 1 (single-document): promise vs delivered reality — reads a shipping intent's Acceptance Criteria, its scope conditions and the delivered code diff, and emits one VSA-shaped verdict JSON: a per-criterion acceptance verdict, a honoured/diverged/missing audit, and a disposition for each scope…
lifeboat-reviewer
Audit a packed lifeboat against its source repo; return a registered verdict (SHIP / NEEDSWORK / MAJORRETHINK) and findings that each cite a packed lifeboat file. Host-delegated; feeds abcd disembark review --review-json.
ruthless-reviewer
Demanding senior code review at a Linus/Carmack bar. Use PROACTIVELY on any non-trivial diff before presenting it to the user — correctness, resource handling, error paths, API misuse, dead code.
docs-currency-reviewer
Semantic docs-currency review — verifies every user-facing claim against the code that implements it. Use PROACTIVELY before tagging any release, and after merging behaviour changes that docs describe.
reviewer
Grades a diff against the spec and tests. Returns a JSON verdict. Makes no changes.
tldrcrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.