mcpField
R
recall

recall

github.com/rohitg00Agent workflows30.0k14.1k installsUpdated 1d ago
Repository

About recall

recall is an agent skill for finding past context in stored memory and activity. It searches with the user's query, can expand selected results for details, and requires reporting only information returned by the memory tools.

Key features

  1. 01Search memory by query
  2. 02Filter by project or agent
  3. 03Expand selected result details
  4. 04Search memory or observations
  5. 05Report only returned information

Use cases

  1. 01Find a previously saved technical decision
  2. 02Retrieve context from a specific project
  3. 03Review activity captured in past sessions

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/rohitg00/agentmemory --skill recall

After installing, type/recallin Claude Code to confirm it loaded.

Bundled filesEXAMPLES.mdTROUBLESHOOTING.md

Details

From the project README

The user wants to recall past context about: $ARGUMENTS

Quick start

memory_smart_search { "query": "jwt refresh token rotation", "limit": 10 }

Expected output:

2 results across 2 sessions.
[importance 8] decision · "Rotate refresh tokens on every use" (session 7f3a9c21)
[importance 5] code · "limit.ts counts per-IP" (session b21d004e)

Why

Only surface what the tool returned. Never fabricate an observation, a session id, or an importance score. If nothing comes back, say so.

Workflow

  1. Call memory_smart_search with the user's text as query and limit: 10. Pass project when the user scopes to a specific repo and agentId when they request one agent's history. Use targetLayer: "memory" for explicitly saved knowledge, or targetLayer: "observation" for captured activity. Omit it for mixed search.
  2. Search results are compact. Before quoting full content or describing provenance, call memory_smart_search with the selected IDs as a comma-separated expandIds string and the same project, agent, and layer filters. If expansion fails or the record is no longer available, report that limitation; a title alone is not the full fact.
  3. Group expanded observations by session and show the returned type, title, and narrative. Include provenance only when the response supplies it.
  4. Lead with the high-signal observations (importance >= 7).
  5. With memory_recall, inspect matched_count, excluded_by_budget, and content_truncated before treating an empty or shortened response as absent knowledge. Recover full content with memory_smart_search using expandIds and the same project, agent, and layer filters. minimum_budget reports the estimated budget needed for a minimal preview when the budget is too small.
  6. If there are no matches, suggest 2-3 alternative search terms and stop. Do not guess.

Anti-patterns

WRONG: results are empty, so you write "We probably discussed token expiry last week" from assumption.

RIGHT: "No memories matched that query. Try refresh token, session expiry, or auth rotation."

Checklist

  • Every observation shown came from the tool response.
  • Results grouped by session, high-importance first.
  • Empty results trigger alternative-term suggestions, not invention.
  • No session id or score was paraphrased or rounded.

See also

  • remember: the write side; recall retrieves what it stores.
  • recap, handoff, session-history: session-scoped views of the same data.
  • memory-discipline: when to run this search unprompted.

Troubleshooting

See TROUBLESHOOTING.md if memory_smart_search is not available.

Comments

Markdown supported