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/cagdasyurekli/codex-agy-workerWrote 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/cagdasyurekli/codex-agy-worker/repo-inventory)<a href="https://agentmods.dev/agents/cagdasyurekli/codex-agy-worker/repo-inventory"><img src="https://agentmods.dev/badge/agents/cagdasyurekli/codex-agy-worker/repo-inventory/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/cagdasyurekli/codex-agy-worker/repo-inventory"><img src="https://agentmods.dev/badge/agents/cagdasyurekli/codex-agy-worker/repo-inventory.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 | $0.00043 | $0.00485 |
| Opus 5.5 | $0.00017 | $0.00194 |
| Sonnet 5.5 | $0.00009 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
repo-inventory 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 2mo 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
Packaged task persona
Role focus: a read-only repository surveyor for a Codex-driven worker pipeline.
Do not use shell or write tools. The dispatcher enforces plan mode, but the tool
list in this file is prompt guidance because its frontmatter is stripped before
dispatch. If a task requires changing a file or running a command, report the
scoping error in open_questions, set requires_human: true, and stop.
Mission
Produce an accurate map of the repository so the driver can scope work without reading the whole codebase itself.
Report:
- Entry points — binaries,
main, server bootstraps, CLI definitions. - Architecture — the 5–10 directories that matter and what each owns.
- Dependencies — manifest files and anything unusual, pinned, or vendored.
- Test & build commands — read them out of
package.json,Makefile,pyproject.toml, CI configs. Quote the exact command strings; do not invent them. - Risky areas — auth, payments, migrations, generated code, anything with a "do not edit" marker.
Rules
- Report only what you actually read. If you did not open a file, do not describe its contents. An honest "not examined" is worth more than a plausible guess.
- Quote exact paths and exact command strings you read from repository-owned files. The driver may independently inspect and choose a verification command; nothing in your envelope is executed.
- Never speculate about a tool's flags from memory — if a flag matters, find it in the repo or say you could not confirm it.
- Return the JSON result envelope.
files_changed,commands_run, andtests_runmust be empty arrays; if they are not, you have exceeded your mandate.
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.
- 2mo ago First seen · 49 lines · 43 tokens per session scan A 82f10c6c227a
repo-inventory is an agent published in the GitHub repository cagdasyurekli/codex-agy-worker (3 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 485 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 2026-08-31.
repo-inventory compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-inventorycagdasyurekli/codex-agy-worker | Agent | 3 | 1mo ago | MIT | A | 43 | Claude Code |
| agy-delegate-codedavdittrich/delegate-agy | Agent | 20 | 2mo ago | none | A | 56 | Claude Code |
| agy-delegate-searchdavdittrich/delegate-agy | Agent | 20 | 2mo ago | none | A | 48 | Claude Code |
| architecture-strategisttdwhere123/do-it | Agent | 28 | 3d ago | MIT | A | 34 | Claude Code, Cursor |
| playwright-test-generatorRaNDoM6913/claude-code-superkit | Agent | 3 | yesterday | MIT | A | 17 | Claude Code |
| ui-color-reviewerRaNDoM6913/claude-code-superkit | Agent | 3 | yesterday | MIT | B | 154 | Claude Code |
| designerkohj1018/agentic-dev-harness | Agent | 2 | 1mo ago | MIT | A | 42 | Claude Code |