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 keeping-docs-alivegit 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/keeping-docs-alive)<a href="https://agentmods.dev/skills/ainsteinsbr/renata/keeping-docs-alive"><img src="https://agentmods.dev/badge/skills/ainsteinsbr/renata/keeping-docs-alive.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.00966 |
| Opus 5 | $0.00044 | $0.00483 |
| Sonnet 5 | $0.00017 | $0.00193 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade B, and why
keeping-docs-alive scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> Until 0.4.x the method also asked for per-session files in `.claude/sessions/` — field projects proved it dead letter (the folder was never created; the state lived in the plan + Section 5 anyway). The convention was r How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keeping docs alive during execution
Living docs are the nervous system between sessions. Without them kept up to date, the next session (human or AI) starts from scratch or worse — starts off wrong.
There are exactly two carriers of resumable state — no third file:
- The active plan (
docs/superpowers/plans/<plan>.md) — execution truth:Status:, checkboxes, deviations. CLAUDE.mdSection 5 (session layer) — a short prose block: where we stopped, what comes next.
Until 0.4.x the method also asked for per-session files in
.claude/sessions/— field projects proved it dead letter (the folder was never created; the state lived in the plan + Section 5 anyway). The convention was removed in 0.5.0. If you find a legacy.claude/sessions/, it's harmless history — don't create new files there.
When this skill activates
Auto-activates when the context involves:
- "Finished task X" / "task X is done"
- "I'm going to pause" / "stopping for today" / "we'll continue tomorrow"
- "Phase X complete"
- "I decided to change the approach to Y"
- "I'm going to open a PR / final commit"
- A plan checkbox being marked as complete
Procedure (2 mandatory steps)
Step 1 — Update the active plan
If the current work corresponds to a task in the plan at docs/superpowers/plans/<plan>.md:
- Check the checkboxes of the completed steps:
[ ]→[x]. - Add a note if the task deviated from the plan (e.g., "I had to add X because Y").
- Update the count if there's a "completed: N/M" field in the plan.
Step 2 — Update CLAUDE.md
Section 4 (Feature layer) — if there was a phase/feature change:
**Fase ativa:**should point to the actual phase in progress.**Feature-âncora:**likewise.
Section 5 (Session layer) — whenever you pause/resume, refresh the resumable-state block:
**Plano ativo:** `docs/superpowers/plans/<file>.md` · **Última task:** Task N (Step N.M)
**Próxima ação:** <1 specific sentence>
**Pegadinhas:** <only if discovered this session — 1-2 lines, or omit>
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.
- 8d ago First seen · 75 lines · 87 tokens per session scan B d7b931d1bffa
keeping-docs-alive is a skill published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 17d ago), licensed MIT. It adds 87 tokens to every session and 966 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
collaboration-platform-administration
Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal…
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…
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…
documentation-patterns
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation, writing architecture decisions, documenting APIs, or maintaining changelogs.
join-meeting
AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports audio-only mode with voice intelligence (barge-in, interruptions), text-to-speech mode, and webpage modes for custom UI. Use when asked to join a call, attend a meeting, or participate in a…