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 escoffier-labs/brigade --skill card-refreshgit clone --depth 1 https://github.com/escoffier-labs/brigadeWrote 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/escoffier-labs/brigade/card-refresh)<a href="https://agentmods.dev/skills/escoffier-labs/brigade/card-refresh"><img src="https://agentmods.dev/badge/skills/escoffier-labs/brigade/card-refresh/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/escoffier-labs/brigade/card-refresh"><img src="https://agentmods.dev/badge/skills/escoffier-labs/brigade/card-refresh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 37 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00056 | $0.00854 |
| Opus 5.5 | $0.00022 | $0.00342 |
| Sonnet 5.5 | $0.00011 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
card-refresh 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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
card-refresh
Safely refresh stale memory cards that memory care already queued. Brigade does not run the agent; this skill is the allowlist-bound recipe an operator invokes on their own harness and schedule.
When this applies
brigade memory care scan(or import-issues) has produced a refresh queue.- An operator schedules a headless harness against this skill for safe auto-refresh.
- Card categories in scope are on the operator's category allowlist.
Allowlist
Work only through this allowlist:
- Read the care refresh queue (
.brigade/memory-care/decay/refresh-queue.jsonor the workspace's configured legacy path) brigade memory care statusbrigade memory care plan-fixes(planning only; writes no cards)brigade memory care closeoutwhen finishing reviewed queue items- Read/Grep of the card file, its cited evidence paths, and related on-disk sources of truth
- Edit only cards whose category is on the operator allowlist for this run
Bash is scoped to those brigade memory care … commands only. Do not touch cards outside the category allowlist. Stay inside the allowlist above; do not follow .. or symlinks out of the card / care-queue roots.
Grounded-edit rules
Refreshes must be grounded. Edit or refresh a card only when you can cite existing on-disk content that verifies the change (the card body, linked evidence files, handoffs, or other local sources of truth). Never date-bump alone. If you cannot verify a claim against on-disk material, skip the card and leave it queued for a human.
Retention (never delete)
- Never delete memory cards.
- Never remove cards from the corpus with destructive ops.
- Never prune the refresh queue or card trees by hand.
- Archive only when an operator-approved archive path already exists; otherwise leave stale-but-unverified cards for human review and use
care closeoutfor items you actually refreshed.
Reinforce over duplicate (#724)
Ingest already reinforces exact fingerprint matches and proposes near-match / opposite-polarity review. When refreshing:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 69 lines · 56 tokens per session scan A 57cd0ebff774
card-refresh is a skill published in the GitHub repository escoffier-labs/brigade (81 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 854 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
plur-create-engrams
Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.