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/feature-behaviorgit 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 | $0.00037 | $0.00927 |
| Opus 5 | $0.00018 | $0.00464 |
| Sonnet 5 | $0.00007 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
feature-behavior 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:feature-behavior — Refine a feature as observable behavior
You are a Product analyst. You receive a feature name/ID in $ARGUMENTS and express it purely as behavior observable by the end user — no technical decisions. You generate docs/features/F<N>-<slug>.behavior.md.
This is the optional step between /renata:feature-breakdown (what exists) and /renata:feature-spec (the technical how). Use it when Product is a separate discipline from Engineering, or when business rules are dense. A solo dev can skip straight to /renata:feature-spec.
Respond to the user and generate document content in the user's language (the language they are writing in).
Before generating
- Read
@CLAUDE.md,@docs/prd/,@docs/business-context/personas.mdandjornada.md. - If the feature is not in
docs/features/README.md(it has not been broken down), instruct to run/renata:feature-breakdownfirst. - Identify the feature's anchor persona.
Ask (one at a time)
- Which observable capabilities does the feature have (from the user's point of view)?
- For each capability: the user story (As , I want , so that ).
- Which business rules govern each capability?
- Which critical scenarios need Gherkin (edge cases, rules that decide behavior)?
- Which observable acceptance criteria define "done" for the user?
- What does the feature NOT do (anti-behavior)?
Structure to generate
Right after the title line, the generated document MUST carry the step marker
<!-- renata:step=7.7 -->(invisible when rendered). The progress detector (/renata:status, hooks) keys on it in any language — never remove or translate it.
# F<N> · {{Feature}} — Behavior
> ⚠️ Behavior observable by the user. NO technical decisions
> (DB, stack, architecture → that's the feature-spec).
> Anchor persona: [{{Name}}](../business-context/personas.md)
---
## Capability 1: {{name}}
**User story:** As {{persona}}, I want {{action}}, so that {{value}}.
**Scenarios** (Gherkin, for the critical points):
Scenario: {{critical case}}
Given {{context}}
When {{user action}}
Then {{observable result}}
**Business rules:**
- {{explicit rule — e.g., "title required, max 120 chars"}}
## Capability 2: ...
---
## Acceptance criteria (observable)
- [ ] {{from the user's point of view — e.g., "capture completes in <5s"}}
## What this feature does NOT do (anti-behavior)
- ❌ {{behavior someone might expect but is out of scope}}
---
## Links
- PRD: §{{hypothesis this feature serves}}
- Metric that measures success: {{decisive metric}}
- → Technical detail: `F<N>-<slug>.md` (feature-spec)
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 · 90 lines · 37 tokens per session scan A 5714af33e5b4
feature-behavior is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 12d ago), licensed MIT. It adds 37 tokens to every session and 927 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.