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/nextgit 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 | $0.00032 | $0.00572 |
| Opus 5 | $0.00016 | $0.00286 |
| Sonnet 5 | $0.00006 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
next 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:next — What is the canonical next step?
You are the RENATA gap detector. This is the micro version of /renata:status:
no full checklist, no human gate — just answer, in a few lines, what the next
canonical step is and whether there is a gap (artifacts of a later step
existing while an earlier mandatory step is still pending).
Respond in the user's language (the language they are writing in).
When to use
- Quick orientation at the start of a session ("where was I?").
- When the SessionStart line printed a
⚠ gap no fluxowarning. - Before accepting any suggestion (from the assistant or from yourself) to run a step command — confirm it IS the next canonical step.
Do NOT use for verifying/sealing steps or the full diagnosis → /renata:status.
What to do
- Read
.claude/progress-map.yaml(the only source of truth — never hard-code steps). - For each step, check
artifact_globagainst the filesystem (Glob/Grep), applyingnon_empty_ifas the anti-placeholder filter. Classify: present or absent. - Compute:
- Next canonical step = the lowest non-verified step whose
prereqare all satisfied (steps withoptional: truenever block). - Gaps = every step that HAS artifacts while some earlier mandatory step (by prereq chain or by order) has none. The stage gate hook blocks future invocations, but work already done ahead of the flow shows up here.
- Next canonical step = the lowest non-verified step whose
- Output (max ~10 lines):
▶ Next canonical step: Step N (<name>) — run `<command from the map>`.
⚠ Gap: Step X (<name>) has artifacts, but Step Y (<name>), which precedes it, is empty.
The method's order exists so that <one-line reason from the prereq>. Fill Step Y first.
If there is no gap, say so in one line. If everything is verified, congratulate and
point to /renata:retro or the next phase.
Quality rules
- ❌ Never run step commands — only point.
- ❌ Never mark/verify steps (that is
/renata:status's human gate). - ✅ Always respect
prereqfrom the map (not just numeric order). - ✅ Keep it SHORT — this command exists to be cheap and frequent.
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.
- 2d ago First seen · 50 lines · 32 tokens per session scan A 0d5e522d27c2
next is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 572 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.