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.
npx agentmods add commands/ainsteinsbr/renata/statusgit clone --depth 1 https://github.com/AInsteinsBR/renataWhat 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 | $0.00031 | $0.01830 |
| Opus 5 | $0.00015 | $0.00915 |
| Sonnet 5 | $0.00006 | $0.00366 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
status 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 3d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:status — Where I am in RENATA and what the next step is
You are the RENATA navigator. Your job is to tell the user, precisely, which step of the flow (steps 1–13, plus the optional sub-steps 1.5, 6.5, 7.7 and 8.5) the project is in, what is missing, and which command to run next — without ever running the step commands for them.
Source of truth
ALWAYS read .claude/progress-map.yaml. It describes each step: num, name,
command, artifact_glob, non_empty_if, optional, prereq, validation.
Never hard-code steps in this prompt — the map is the only source.
Three state levels per step
- ⬜ Pending — no file matches
artifact_glob, OR the file exists but does not contain thenon_empty_ifsubstring (= placeholder only). - 🔄 In progress — the file exists and has real content, but does NOT have, in the first 5 lines, the
line
> ✅ Verified by you on <date>. - ✅ Verified — some file of the step has, in the first 5 lines, the line
> ✅ Verified by you on <date>.
What to do (in order)
1. Read the map and scan the docs
Read .claude/progress-map.yaml. For each step, check the artifact_glob against
the filesystem (use Glob/Grep). Classify each step as ⬜ / 🔄 / ✅ by the
rule above.
2. Show the visual progress map
Print the list of ALL steps from the map, one per line, in the format:
✅ 1 · Create the project
✅ 2 · Define the product (PRD)
🔄 3 · Map personas
⬜ 4 · Map journeys
⬜ 8.5 · Screen design (optional)
...
Steps with optional: true get the suffix "(optional)".
3. Point to the next step (respecting prereq)
The next step is the lowest non-✅ step whose prereq are all ✅ (or with no
prereq). Do NOT blindly point to the next numeric step — the method allows alternative
paths (see Appendix C of REFERENCE.md: a technical project does ADRs before
personas, etc). Steps with optional: true do not block the next step.
State clearly: "Next step: Step N (). Run <command from the map>."
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.
- 3d ago First seen · 125 lines · 31 tokens per session scan A f71c7a8cfbfb
status is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 12d ago), licensed MIT. It adds 31 tokens to every session and 1,830 once invoked, about $0.0002 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 commands, from other repositories
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
issue-closeout
Triage Codex findings via per-finding dispositions, mark findingstriaged, close the active issue.
prd-review
Review the active PRD with Codex and stream normalized findings to JSONL.
prd-triage
Triage pending findings on the active PRD.
prd-archive
Archive the active PRD (terminal state).
issue-start
Load a DSSE issue spec and begin structured work.