prune-memory SKILL.md skillA
prune-memory from tylerjrbuell/reactive-agents-ts is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tylerjrbuell/reactive-agents-ts/prune-memory@git:20261103.92630caPins git:20261103.92630ca in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tylerjrbuell/reactive-agents-ts
- Path
.agents/skills/prune-memory/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261103.92630ca, committed Nov 3, 2026
- First version recorded
- Apr 20, 2026
- Size
- 5,886 bytes
- Repository stars
- 31
- License
- MIT
Audit project memory (.agents/MEMORY.md and ~/.claude/.../memory/MEMORY.md) against current code and remove stale claims to prevent bad signals in future sessions.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Prune Memory ## Overview Memory decays. File paths get renamed, dead code gets deleted, "open blockers" get fixed, test counts drift. Stale memory silently poisons every future session — you recommend a function that no longer exists, cite a bug that was fixed, skip a fix because memory said it was already done. This skill audits every verifiable claim in memory against current code state and removes or updates whatever has drifted. **Run this:** before major architecture decisions, before a release audit, when memory contradicts observed reality, or once a month as hygiene. ## Scope Two memory files are in scope: 1. `.agents/MEMORY.md` (repo-committed, shared with other AI agents) 2. `~/.claude/projects/-home-tylerbuell-Documents-AIProjects-reactive-agents-ts/memory/MEMORY.md` (Claude auto-memory) Both must end the skill in sync. ## What counts as a verifiable claim Only audit claims the code can falsify. Skip subjective or conversational notes. | Audit these | Skip these | |---|---| | File paths, line numbers, exports | User preferences, feedback memories | | Function/class names, symbol existence | Architectural philosophy, design rationale | …
Read the whole file at its exact version.
How to install
mdr add tylerjrbuell/reactive-agents-ts/prune-memory@sha256:321615046f06d489The line at the top of this page pins the label git:20261103.92630ca, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_whprnkigf6n6f7cf)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 20, 2026 and Nov 3, 2026, about one every 49 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261103.92630ca latest | 2026-11-03 | 92630ca | 5,886 B | A | view · diff |
| git:20261103.bf74aa0 | 2026-11-03 | bf74aa0 | 6,031 B | A | view · diff |
| git:20260804.2e6a1f9 | 2026-08-04 | 2e6a1f9 | 6,037 B | A | view · diff |
| git:20260603.a12f37b | 2026-06-03 | a12f37b | 6,068 B | A | view · diff |
| git:20260420.cd26a29 | 2026-04-20 | cd26a29 | 6,079 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5886 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
tylerjrbuell/reactive-agents-ts · 31 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_whprnkigf6n6f7cf GET https://markdownregistry.com/api/v1/resolve?ref=tylerjrbuell/reactive-agents-ts/prune-memory GET https://markdownregistry.com/api/v1/blob/321615046f06d489ac4246f3c081d10aff9e62366ee83cd73b690f00e7c910c8
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.