memory-recall
Skill75 starsChanged 4 months agoMITView on GitHub
Runtime-neutral recall from the Coven shared memory store (~/.coven/memory). Wraps the coven-memory CLI to retrieve promoted, attested facts at query time. Read-only by construction.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- kriscard/Skillstheir own version, first seen Oct 28, 2026
- opensite-ai/opensite-skillstheir own version, first seen Oct 13, 2026
- cerebrocybersolutions/librotheir own version, first seen Oct 4, 2026
- haraldalder-vibemogger/project-memorytheir own version, first seen Sep 26, 2026
- NITISH-R-G/agent-memory-protocoltheir own version, first seen Aug 1, 2026
- star-ga/mind-memtheir own version, first seen May 6, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- star-ga/mind-mem★ 22same name
- kriscard/Skills★ 15same name
- opensite-ai/opensite-skills★ 15same name
- haraldalder-vibemogger/project-memory★ 2same name
- cerebrocybersolutions/libro★ 1same name
- NITISH-R-G/agent-memory-protocol★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/heygen-skills/CLAUDE.mdCLAUDE.md
- 1passwordSkill
- ask-curlSkill
- boardSkill
- cleanup-unused-filesSkill
- codeflow-maintainerSkill
- codex-session-managerSkill
- coven-astraSkill
- coven-board-entrySkill
- coven-charmSkill
- coven-cloud-maintainerSkill
- coven-codySkill
- coven-echoSkill
- coven-identity-canonSkill
- coven-kittySkill
- coven-parallel-workSkill
- coven-sageSkill
- coven-task-managerSkill
- daily-dev-agenticSkill
- discrawlSkill
- disk-space-optimizerSkill
- epubSkill
- familiar-board-stewardshipSkill
- heygen-avatarSkill
- heygen-videoSkill
- heygen-skillsSkill
- higgsfield-generateSkill
- higgsfieldSkill
- linear-issue-managementSkill
- lit-ui-designerSkill
- lobsterSkill
- maintainer-barSkill
- memory-timeline-managerSkill
- ml-engineerSkill
- nodriverSkill
- ocrSkill
- openclaw-devSkill
- openclaw-trustSkill
- opencoven-designSkill
- OpenCoven Role Creation ProcessSkill
- pr-agentSkill
- project-managerSkill
- prompt-engineerSkill
- prompt-vaultSkill
- research-ingestionSkill
- ritual-dapp-frontendSkill
- rollcallSkill
- security-agentSkill
- skill-scannerSkill
- slidev-deck-pipelineSkill
- tauri-apple-releaseSkill
- threejs-animationSkill
- tinyfish-agent-runSkill
- tinyfish-browserSkill
- tinyfish-fetchSkill
- tinyfish-searchSkill
- tinyfishSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 67
Query the crate: Treat query and familiar as untrusted data.
- Distinctive: line 82
Never silently hide a superseded claim — the store is a claims log (§11.0).
- Very specific: line 114
No shell, runtime-specific hooks, session APIs, or bootstrap injection are required.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Memory Recall
Retrieval-side contract for the Coven memory layer (Authoritative Plan v1 hole #7;
issue the memory recall implementation). Any familiar, under any runtime, uses this skill to pull
already-promoted facts back into working context. It does not write, promote,
or mutate anything under ~/.coven/memory — that is the promotion layer's job
(schema: familiar-contract/schemas/coven-memory-schema.md §11). A
coven memory promote command is planned but does not exist yet; see
docs/memory/attested-promotion.md.
When to use
- The question depends on a promoted Coven fact, decision, or cross-familiar context rather than the current session or the familiar's own MEMORY.md.
- "Did we decide X?" / "what did
<familiar>attest about Y?" for anything that plausibly predates the current session or originated with another familiar. - As a supplement to the runtime's own memory search (which covers per-familiar MEMORY.md / daily notes / transcripts). Recall covers the layer below that: promoted, attested, cross-familiar-visible.
When NOT to use
- Answer is in the current session → just answer.
- Answer is in the familiar's own MEMORY.md or daily files → use the runtime's memory tools.
- The promotion layer has not run for the relevant window → recall returns empty; say so honestly. Never fabricate a hit.
Inputs
| Field | Type | Required | Description |
query | string | ✅ | Natural-language question or keyword phrase. |
familiar | string | ❌ | Store scope filter passed to the crate: coven (default; the shared store) or a familiar id for per-familiar stores. Must match ^[A-Za-z0-9_-]{1,128}$ — the same shape the crate's own validate_identifier enforces for familiar_id. |
k | int | ❌ | Max results. Default 5, max 20. |
since / until | ISO date | ❌ | Filter on manifest timestamp. |
verified_only | bool | ❌ | Default true. Drop hits whose manifest sha256 no longer matches the promoted snapshot or whose attested_via file is missing. |
Outputs
| Field | Type | Description |
hits | array | Ordered {ulid, title, type, memory_type, snippet, score, attested_by, attestation_type, promoted_at, superseded_by?} |
count | int | Length of hits. |
queried_at | RFC3339 UTC | When the recall ran. |
manifest_hash | string | SHA-256 of manifest.jsonl consulted (drift detection between calls). |
dropped | int | Hits removed by verification (verified_only=true). Surfaced, never silent. |
Side effects
None. Recall is read-only by construction; an implementation that mutates
~/.coven/memory during recall is non-conformant with this skill. Recall MUST NOT
log query text to any destination outside the Coven filesystem.
Steps
- Precondition.
~/.coven/memory/manifest.jsonlexists with ≥1 line, else return{hits: [], count: 0, note: "promotion layer has not run"}and stop. - Query the crate. Treat
queryandfamiliaras untrusted data. Validatefamiliaragainst^[A-Za-z0-9_-]{1,128}$(defaultcoven) — the shape the crate'svalidate_identifieralready enforces — and reject any other value. Invoke the crate with an argv API, not a shell command string, equivalent toexecve/subprocess.run(["coven-memory", "search", "--familiar", familiar, query]). If a runtime exposes only a shell, pass every dynamic argument through robust single-argument shell escaping (for example Pythonshlex.quote) and do not concatenate raw input. Add--index/--dbonly if the store lives off the default path. The crate owns ranking (fastembed/nomic-embed-text-v1.5 + TurboVec ANN; schema §11.5 pins embeddings as crate-internal). - Join against the manifest. For each hit, find its manifest line by
ulid. Applysince/untilontimestamp. Detect supersession: if a lateroperation: supersedeline names this ulid asprior_ulid, annotatesuperseded_byand rank the superseding entry ahead of the superseded one. Never silently hide a superseded claim — the store is a claims log (§11.0). - Verification (
verified_only=true, default). Drop hits where (a) the manifestsha256mismatches the promoted snapshot content, or (b) the entry'sattested_viaattestation file is absent. Count them indropped. Fail-degraded, not fail-fatal: verification failure removes the hit and is reported; it never aborts the query. (No cryptographic verification in v1 — attestations are unsigned per schema §11.2.) - Resolve
source_contextlazily. Entries carry FAMILIAR_ROOT-relative paths or portablesession://references (§11.1). Resolve against the current environment's FAMILIAR_ROOT (--familiar-rootflag →COVEN_FAMILIAR_ROOTenv) only when the caller asks to open a source; unresolvable → return the portable reference as-is with a note. Recall never requires FAMILIAR_ROOT to answer. - Answer with provenance. Present claims with
attested_by+attestation_typeconfidence+ timestamp. Conflicting claims are both returned; the querying familiar reasons over them (claims-log framing, §11.0).
Failure modes
| Condition | Behavior |
| Store or manifest missing | Empty result + honest note. Never fabricate. |
coven-memory binary absent | Fail with install pointer (OpenCoven/coven crates). No grep fallback that bypasses scope filtering. |
| Manifest line missing for a hit | Drop hit, count in dropped (index-without-source is a defect, §11.0). |
Unknown scope/fields in a manifest line | Skip that line, count in dropped (fail-degraded). |
Runtime-Portability Audit (§11.5 — answered)
If Val runs a familiar tomorrow under a different runtime (Codex CLI, Cursor, Claude Code, CovenCave, bare SSH), does this skill work without modification?
✅ Yes. The skill's only dependencies are (a) the coven-memory CLI — a
Coven-shipped binary, and (b) ~/.coven/memory/ — a Coven-owned contract path.
No shell, runtime-specific hooks, session APIs, or bootstrap injection are
required.
FAMILIAR_ROOT resolution follows the schema's flag→env→fail-closed order and is
only needed for optional source opening, never for querying. Session references
use the portable session:// class form, never raw runtime session keys.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

