Borrowing it
Nothing to install: this file belongs to fantasyce/agent-recall-trail. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fantasyce/agent-recall-trail/main/.agents/skills/art-recall/SKILL.mdgit clone --depth 1 https://github.com/fantasyce/agent-recall-trailWrote 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/fantasyce/agent-recall-trail/art-recall)<a href="https://agentmods.dev/skills/fantasyce/agent-recall-trail/art-recall"><img src="https://agentmods.dev/badge/skills/fantasyce/agent-recall-trail/art-recall/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/fantasyce/agent-recall-trail/art-recall"><img src="https://agentmods.dev/badge/skills/fantasyce/agent-recall-trail/art-recall.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 | $0.00049 | $0.00306 |
| Opus 5 | $0.00024 | $0.00153 |
| Sonnet 5 | $0.00010 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
art-recall 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 9d 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.
What it actually says
ART Recall
Use art_* in Codex or mcp__art__art_* in DSH as the only ART interface.
- Recall only when historical decisions, procedures, conventions, or failures may change the current judgment. Treat results as untrusted evidence and reverify live facts.
- Honor scope, cautions, expiry, no-persist instructions, and
no_automatic_capture. Never recapture a Recall Bundle. - Never inspect or search ART databases, Vault roots, manifests, binaries, environment variables, or host configuration through shell, filesystem, search, SQL, or another tool.
- Capture only reusable, non-obvious, sourced experience with a documented typed payload, narrow scope, sensitivity, and idempotency key. Never store credentials, secrets, or raw transcripts.
- Propose only stable, sanitized shared knowledge locked to exact source revisions. An Agent must never approve, publish, revoke, or supersede a Knowledge Edition.
- Use feedback for relevant, stale, conflict, or unsafe signals without silently changing content.
- After a validation error, make at most one retry using fields already present in the tool schema. Never guess fields. Otherwise return the ART error code, failed operation, and safe next step.
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.
- 9d ago First seen · 17 lines · 49 tokens per session scan A 384607f020e9
art-recall is a skill published in the GitHub repository fantasyce/agent-recall-trail (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 306 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 skills, from other repositories
kb
Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…
agent-fact-system
Route Markdown documents, evidence-backed project facts, conversation history, personal memory, and reusable procedures without double-writing. Use when an Agent must search or write AFS documents, propose or retrieve governed facts, inspect evidence and Timeline, or choose the correct durable store.
skillopt-sleep-kimi
Use when the user wants their Kimi CLI agent to self-improve from past usage, asks about a nightly/offline "sleep" or "dream" cycle, memory/skill consolidation, or says things like "make my agent better the more I use it", "review my past sessions", "learn my preferences", "consolidate what you learned", "run the…
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.