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 skills add AInsteinsBR/renata --skill respecting-adrsgit clone --depth 1 https://github.com/AInsteinsBR/renataWrote 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/skills/ainsteinsbr/renata/respecting-adrs)<a href="https://agentmods.dev/skills/ainsteinsbr/renata/respecting-adrs"><img src="https://agentmods.dev/badge/skills/ainsteinsbr/renata/respecting-adrs/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/skills/ainsteinsbr/renata/respecting-adrs"><img src="https://agentmods.dev/badge/skills/ainsteinsbr/renata/respecting-adrs.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 | $0.00071 | $0.00861 |
| Opus 5 | $0.00036 | $0.00430 |
| Sonnet 5 | $0.00014 | $0.00172 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
respecting-adrs 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Respecting ADRs before coding
ADRs (docs/decisions/ADR-*.md) are the project's structural decisions with status accepted. Every technical proposal must respect them — a violation requires opening a new superseding ADR, not bypassing them.
When this skill activates
Auto-activates when the context involves:
- "Implement X"
- "I'm going to write / code / create"
- "Which library to use"
- "How do I Y in [language/framework]"
- "Refactor to use Z"
- Proposing a diff/PR
Procedure (4 steps)
Step 1 — List the relevant accepted ADRs
Run this mentally: "Which ADRs in this project might have something to say about what I'm about to do?"
- Always consult
docs/decisions/README.md(the index). - If the proposal touches: database → ADR about persistence; auth → ADR about auth; external libraries → ADR about the stack; etc.
- If there is no ADR on the topic but the decision is structural → open an ADR first (
/adr).
Step 2 — Validate the proposal against each identified ADR
For each relevant ADR:
- Read the "Decision" and "Enforcement" sections.
- Confirm that the proposal does not contradict the decision.
- If the ADR has a hook (
.claude/rules.yaml), make sure your code won't be blocked by it.
Step 3 — If there's a conflict, STOP
Don't code. Options:
- Refine the proposal to respect the ADR (most common).
- Open a new ADR superseding the old one, if the old decision really is wrong (use
/adr). - Ask the user for clarification if the conflict isn't clear.
NEVER work around the hook or use a silent workaround.
Step 4 — Cite the ADR in the commit/PR
When implementing, mention the relevant ADR:
feat(providers): ClienteRepo em providers/impl (ADR-007 adapter pattern)
Examples
✅ Good
User: "I'm going to add a cache lib to the worker to store responses."
Skill activates: "Before coding, I'll consult the ADRs.
ADR-004defines technology X for path A, OK. But this cache is a different kind (key-value) and ADR-004 doesn't cover that use. I'll reuse the same infrastructure already available with a dedicated prefix. It doesn't violate ADR-004 or create a new structural decision (caching is an implementation detail)."
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.
- 10d ago First seen · 85 lines · 71 tokens per session scan A 27147342f2ac
respecting-adrs is a skill published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 20d ago), licensed MIT. It adds 71 tokens to every session and 861 once invoked, about $0.0004 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 skills, from other repositories
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
write-prd
Write PRD — Product Requirements Documents with structured 8-section templates, user stories, acceptance criteria, and value proposition validation. Use when writing PRDs, defining product requirements, creating user stories with INVEST criteria, or building go/no-go decision frameworks.
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…