agentmemory
Use when saving, recalling, resuming, forgetting, summarizing, or listing Agentmemory project memories and sessions, including commit history and commit…
Skill by shiyuan17
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/shiyuan17-agentmemory
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agentmemory
What's inside
- Skill name
agentmemory- Description
- Use when saving, recalling, resuming, forgetting, summarizing, or listing Agentmemory project memories and sessions, including commit history and commit context lookup.
- License
- MIT
- Instructions
- 28 lines in SKILL.md · view on GitHub
Files (8)
- SKILL.md
- audit.md · references/
- forget.md · references/
- handoff.md · references/
- recall.md · references/
- recap.md · references/
- remember.md · references/
- session-history.md · references/
SKILL.md (first lines)
# Agentmemory 集成 使用 Agentmemory 保存、检索、恢复和解释跨 session 的项目记忆。根据当前意图只读取对应流程: - 恢复最近相关 session:读取 [references/handoff.md](references/handoff.md)。 - 检索历史观察、决策或经验:读取 [references/recall.md](references/recall.md)。 - 保存长期事实、决策或经验:读取 [references/remember.md](references/remember.md)。 - 删除明确的 memory:读取 [references/forget.md](references/forget.md)。 - 汇总指定时间窗口的 sessions:读取 [references/recap.md](references/recap.md)。 - 列出可选择的 session 时间线:读取 [references/session-history.md](references/session-history.md)。 - 审计本地记忆的陈旧、重复或矛盾:读取 [references/audit.md](references/audit.md)。 先检测 agentmemory MCP;不可用时可使用已配置且获授权的 HTTP API。两者均不可用时回退到 `.agents/memory/` 和当前仓库事实,并明确没有访问外部记忆。 提交历史查询直接走本入口:需要历史列表时解析 `branch`、`repo`、`limit` 后调用 `memory_commits`,HTTP 回退为 `GET $AGENTMEMORY_URL/agentmemory/commits`,query 必须 URL 编码并从 `AGENTMEMORY_SECRET` 读取凭据。需要提交上下文时先用 `git blame -L`、`git log -L` 或 `git log -n 1 -- <file>` 定位完整 SHA,再调用 `memory_commit_lookup`,HTTP 回退为 `GET $AGENTMEMORY_URL/agentmemory/session/by-commit?sha=<encoded-sha>`;必要时用 `memory_recall` 获取高重要度 observation。展示 commit 关联时必须用本地 `git show` 复核,Git 或 agentmemory 不可用时只报告实际可得事实,不得编造关联或意图。 本地记忆库默认位于 `.agents/memory/`: - `CURRENT.md`:唯一恢复入口;若安装了治理记忆(`docs/memory/PROJECT_STATE.md`),经它引用读取、不复制其内容。 - `observations.md` 保存长期观察、陷阱和验证注意事项。 - `decisions.md` 保存已确认的长期决策。 - `sessions/` 保存需要跨 session 恢复的摘要或交接记录。 更新 `CURRENT.md` 时写入锚点提交(更新时刻的 HEAD 完整 SHA)与绝对日期;恢复时核验锚点提交仍是当前历史的祖先。 记忆只能辅助恢复上下文;当前文件、Git 状态、测试输出和用户最新指令始终优先。
From shiyuan17/Vibe-Harness, MIT.
More from shiyuan17/Vibe-Harness
- 0.570score
stale-cleanup
shiyuan17
Use when cleaning dead code, stale references, outdated docs, orphan resources, stale memory, or stale indexes; producing evidence-based removal lists; or…
SkillAFreshness: AClaude Code +9 - 0.567score
clarify-requirements
shiyuan17
Use for unresolved product choices or explicit requirements discovery—not discoverable facts, implementation details, approvals, or final goals.
SkillAFreshness: AClaude Code +9 - 0.565score
systematic-debugging
shiyuan17
Use when a specific failure, error, or flaky test needs its root cause proven before fixing—not for applying known fixes.
SkillAFreshness: AClaude Code +9 - 0.564score
frontend-design
shiyuan17
Use for frontend visual direction, polish, responsiveness, or redesign—not logic-only work.
SkillAFreshness: AClaude Code +9 - 0.564score
define-goal
shiyuan17
Use to write, refine, or activate `/goal` or execution/exploration objectives—not goal status operations.
SkillAFreshness: AClaude Code +9 - 0.561score
vb-git-split-push
shiyuan17
Use only when explicitly requested as Vb Git Split Push, $vb-git-split-push, or legacy $git-deliver to commit task changes in logical groups and push the…
SkillAFreshness: AClaude Code +9 - 0.561score
eval-driven-development
shiyuan17
Use for nondeterministic Agent rules, Skills, prompts, Hooks, or routing—not deterministic logic, bug fixes with known causes, or deterministic refactors.
SkillAFreshness: AClaude Code +9 - 0.561score
vb-git-develop-flow
shiyuan17
Use only when explicitly requested as Vb Git Develop Flow, $vb-git-develop-flow, or legacy gd-flow to deliver through an isolated worktree into develop; never…
SkillAFreshness: AClaude Code +9 - 0.559score
bug-finding
shiyuan17
Use when reviewing existing code for latent logic, flow, feature, state, consistency, requirement, or API bugs with no failing symptom—read-only audit, not…
SkillAFreshness: AClaude Code +9 - 0.558score
task-decomposition
shiyuan17
Use to split implementation plans into a Goal, Task DAG, and prompts for verifiable work.
SkillAFreshness: AClaude Code +9 - 0.558score
api-and-interface-design
shiyuan17
Use for public APIs, schemas, events, config, or consumed module boundaries.
SkillAFreshness: AClaude Code +9 - 0.553score
security-and-hardening
shiyuan17
Use for trust boundaries, untrusted input, auth, secrets, sensitive data, or external writes.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 9, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/shiyuan17/Vibe-Harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from shiyuan17
- 0.570score
stale-cleanup
shiyuan17
Use when cleaning dead code, stale references, outdated docs, orphan resources, stale memory, or stale indexes; producing evidence-based removal lists; or…
SkillAFreshness: AClaude Code +9 - 0.567score
clarify-requirements
shiyuan17
Use for unresolved product choices or explicit requirements discovery—not discoverable facts, implementation details, approvals, or final goals.
SkillAFreshness: AClaude Code +9 - 0.565score
systematic-debugging
shiyuan17
Use when a specific failure, error, or flaky test needs its root cause proven before fixing—not for applying known fixes.
SkillAFreshness: AClaude Code +9 - 0.564score
frontend-design
shiyuan17
Use for frontend visual direction, polish, responsiveness, or redesign—not logic-only work.
SkillAFreshness: AClaude Code +9 - 0.564score
define-goal
shiyuan17
Use to write, refine, or activate `/goal` or execution/exploration objectives—not goal status operations.
SkillAFreshness: AClaude Code +9 - 0.561score
eval-driven-development
shiyuan17
Use for nondeterministic Agent rules, Skills, prompts, Hooks, or routing—not deterministic logic, bug fixes with known causes, or deterministic refactors.
SkillAFreshness: AClaude Code +9
Cite this page
agentmemory skill. Agent Mart. https://agentmart.dev/skills/shiyuan17-agentmemory (last updated 2026-10-24)