agent-memory
Skill1 starsChanged 21 days agoMITView on GitHub
Set up, upgrade, or repair a repository's agent memory: an Open Knowledge Format (OKF v0.2) bundle in agent-memory/ and its CLAUDE.md / AGENTS.md instructions. Migrate a legacy agent-memory.md log into one concept per learning without losing content; use for requests to install persistent repo learnings.
38 other projects use a version of this.
Adopted by
Most recently taken up by
- isaacbitran/agent-memorytheir own version, first seen Nov 8, 2026
- msking18/agent-memory-mcptheir own version, first seen Nov 8, 2026
- komluk/scaffoldingtheir own version, first seen Nov 7, 2026
- MemTether/MemTethertheir own version, first seen Nov 1, 2026
- tigerless-labs/agent-memorytheir own version, first seen Oct 22, 2026
- vindreshsingh/engineering-skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use observability, data-analysis and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillobservability
Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.
Also in 4 projects that use this
shanggqmSkilldata-analysis
数据分析技能,提供结构化的数据查询、统计分析和报告生成工作流。当用户需要查询数据库、进行数据统计分析、生成分析报告时使用。按规范输出原始数据、计算结果、Markdown报告和HTML可视化报告。
Also in 3 projects that use this
Microsoft AzureSkillskill-authoring
Write Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new skill", "write a skill", "skill template", "skill structure", "review skill", "skill PR", "skill compliance", "SKILL.md format", "skill frontmatter", "skill best practices". DO NOT USE FOR: general documentation. INVOKES: vally CLI.
Also in 3 projects that use this
VercelSkilltechnical-writing
Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current source, tests, CLI help, public releases, and repository conventions.
Also in 3 projects that use this
JetBrainsSkillwebapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Also in 4 projects that use this
AnthropicSkillpdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Also in 5 projects that use this
Other versions38 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 38
- tigerless-labs/agent-memory★ 4.3ksame name
- databricks/app-templates★ 218same name
- OpenHands/extensions★ 167same name
- JKHeadley/instar★ 86same name
- nimadorostkar/Claude-Skills-collection★ 33same name
- VoDaiLocz/kilo-kit-mcp★ 28same name
- jayzeng/agentmemory★ 24same name
- komluk/scaffolding★ 16same name
- xChuCx/agent-memory★ 11same name
- t4sh/skills4sh★ 5same name
28 more not listed
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.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.
0
Common
Most of the 33 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Keep durable repo learnings in agent-memory/ at the repository root, an OKF v0.2 bundle: one Markdown concept per learning with YAML …
- Very specific: line 41
If neither exists, use the user's requested file, otherwise CLAUDE.md.
- Very specific: line 42
If they resolve to the same file, edit it once.
- Distinctive: line 47
Leave an identical current block unchanged.
- Very specific: line 49
Read back the result. Check OKF conformance (every non-reserved .md in the bundle has parseable frontmatter with a non-empty type.
“Common” is measured: kept by at least 6 in 10 of the 33 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
Agent memory
Keep durable repo learnings in agent-memory/ at the repository root, an
OKF v0.2
bundle: one Markdown concept per learning with YAML frontmatter, plus the
reserved index.md and log.md. The instruction block
defines the concept format, reading, writing, and first-run migration. The
index and log templates
seed a new bundle. Read all three before editing.
Setup or upgrade
- Confirm the intended repository root. Read existing
CLAUDE.md,AGENTS.md,agent-memory/, andagent-memory.mdbefore writing. Respect an explicitly configured custom memory path; don't silently create a second memory store. Inspect filename case variants as well, especially on macOS and Windows, where existence tests match any case; compare names from a directory listing. - For a fresh repo, copy the index template to
agent-memory/index.mdand the log template toagent-memory/log.md, replacingYYYY-MM-DDwith today's date. Create no concepts. For an existing repo, follow the instruction block's first-run migration rules. Retain all actual entries, custom guidance, dates, commands, uncertainty, and superseded history. Add frontmatter only where the source supports it. Upgrade the block (step 3) before removing the legacy file, so an interrupted run never leaves an old block pointing at a deleted file. To tell stock text from user customizations, compare with the shipped legacy log template and legacy block. - Install or upgrade the managed instruction block in both
CLAUDE.mdandAGENTS.mdwhen both exist as separate files. If only one exists, use it. If neither exists, use the user's requested file, otherwiseCLAUDE.md. If they resolve to the same file, edit it once. Preserve everything outside<!-- agent-memory:start -->/<!-- agent-memory:end -->. - An old block (one without
<!-- simple-agent-memory:instructions=3 -->) is an upgrade target, not a reason to skip setup. Replace a single intact old block with the bundled version, retaining any compatible user customizations. Leave an identical current block unchanged. Append once when absent. For unmatched or multiple marker pairs, or custom instructions conflicting with the upgrade, stop that edit and explain the conflict. - Read back the result. Check OKF conformance (every non-reserved
.mdin the bundle has parseable frontmatter with a non-emptytype;index.mdcarries onlyokf_version), thatindex.mdlists every concept, that relative links resolve, entry coverage, one managed block per instruction file, and consistent memory paths. Report whether this was a fresh install, upgrade, unchanged setup, or blocked migration. Report the recovery location when one was needed. Do not claim unfinished migration succeeded or commit an unresolved partial result.
Plugin updates alone do not edit previously installed repo instructions. Users must invoke this updated setup skill once, or manually install the updated block. The block is self-contained so its first-run migration does not need the plugin.
Scope
Record durable conclusions, root causes, gotchas, and useful dead ends. Keep repeatable procedures and volatile answers in their owning docs or tools and link to them. Don't store secrets or transient task state. Read memory on demand; do not introduce an automatic import of the bundle. Do not change tool-native memory outside the requested repository. A user-requested package-local installation uses the same rules within that package.
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.

