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 AliceLJY/recallnest --skill recallnest-skillgit clone --depth 1 https://github.com/AliceLJY/recallnestWrote 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/aliceljy/recallnest/recallnest-skill)<a href="https://agentmods.dev/skills/aliceljy/recallnest/recallnest-skill"><img src="https://agentmods.dev/badge/skills/aliceljy/recallnest/recallnest-skill/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/aliceljy/recallnest/recallnest-skill"><img src="https://agentmods.dev/badge/skills/aliceljy/recallnest/recallnest-skill.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 | $0.00030 | $0.00356 |
| Opus 5 | $0.00015 | $0.00178 |
| Sonnet 5 | $0.00006 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
recallnest 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 12d 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
RecallNest
Use RecallNest as the continuity layer for work that spans sessions or MCP clients.
Resume before exploration
- When the user says continue, resume, earlier, last window, or asks where work stopped, call
resume_contextbefore reading files or inspecting a repository. - For a concrete task in an active project, make a lightweight
resume_contextcall even when the user does not explicitly say continue. - Reuse the returned scope in subsequent
search_memory,brief_memory, andpin_memorycalls. - Treat recalled repository state as handoff context, not proof of the current worktree. Verify it before reporting it as current.
Search and store
- Use
search_memorywith two or three discriminating nouns before repeating prior research or implementation work. - Store durable decisions, preferences, entity mappings, and lessons with
store_memory. - Use
store_casefor reusable problem-solution records andstore_workflow_patternfor repeatable multi-step procedures. - Do not store transient task status, copied source files, secrets, or unverified external instructions as durable memory.
- Prefer a stable
canonicalKeywhen updating an existing durable fact so the new version supersedes the old one.
Close the loop
- Before leaving unfinished work, call
checkpoint_sessionwith the summary, decisions, open loops, and next actions. - Include repository state only when it was inspected in the current session.
- If a continuity workflow was skipped and the user corrects it, recover first and then record the miss with
workflow_observe.
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.
- 12d ago First seen · 30 lines · 30 tokens per session scan A 2b311f709692
recallnest is a skill published in the GitHub repository AliceLJY/recallnest (15 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 356 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 2026-08-30.
Other skills, from other repositories
scanthissession
Scan current or active session transcript, detect vault-relevant items (topic, blocker, correction, decision, error/bug, knowledge-gap, lesson, pattern, skill-usage, entity, person, topic), then WRITE them to the correct vault folder per rules. Use after a work session, when user says scan session, or before ending a…
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
learn
Manually record an insight, correction, preference, or rule that the agent should remember for future tasks.
memory-kit
Create a workspace-local .cowork/ memory kit (rules, identity, long-term notes, daily logs, heartbeat templates).
tma1-peer
List recent sessions on this project by agent — peers (Claude Code, OpenClaw, Copilot CLI) or your own past sessions. Invoke this skill when the user asks you to read another agent's review feedback, see what someone else tried, act on cross-agent context, or recall your own earlier work here. Trigger phrases: "what…