Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/awrshift/agent-memory-kit/close-sessionnpx skills add awrshift/agent-memory-kit --skill close-sessiongit clone --depth 1 https://github.com/awrshift/agent-memory-kitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00064 | $0.00864 |
| Opus 5 | $0.00032 | $0.00432 |
| Sonnet 5 | $0.00013 | $0.00173 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
close-session scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to close-session — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/close-session — the end-of-session ritual
You close the session in four steps. Don't just dump — audit. Everything you write, you announce briefly; anything promoted to rules/concepts needs the user's verbal "yes" first.
Step 1 — Capture what's new
Scan this session for observations worth keeping. Append each to .claude/memory/MEMORY.md
as a ONE-LINE [YYYY-MM-DD]-prefixed entry. Short, scannable, no essays (long rationale
belongs in a concept article, step 2).
Step 2 — Audit & promote (the valuable part)
Read the date-tagged entries in MEMORY.md. Look for repetition: did this pattern appear on 3+ different dates? Surface 2-4 candidates, be specific: "noticed [date], [date], [date] you said X — codify as a rule or a concept article?"
- User says yes → write
knowledge/concepts/<topic>.md(facts + rationale; frontmatter perknowledge/index.mdspec) or.claude/rules/<name>.md(mechanical always/never constraint; only for patterns stable 6+ months). Updateknowledge/index.md(one line per concept). - Promoted or long-absorbed entries get PRUNED from MEMORY.md — that's how it stays under its caps (180 lines / 32 KB / 3000 chars per line).
- Writing a fact into a second place?
reference/doc-governance.md— one SSOT per fact, and when a fact changes you grep its restatements in the same pass. A product or architecture decision goes to the ledger instead —projects/<name>/decisions-log.md, format inreference/decisions-log.md. A plan, a spec, a research finding or a QA record is NOT memory: it belongs in that project's folder, per the map in itsREADME.md.
Step 3 — Refresh the MEMORY.md header
The header (everything above the first ---) is «current state of work», 2-3 sentences,
REPLACED every close — never a chronicle of past sessions. Per-session detail lives in the
handoff, not stacked in the header.
Step 4 — Write the handoff
Copy context/handoffs/HANDOFF-TEMPLATE.md → context/handoffs/<topic>-<YYYY-MM-DD>.md and
fill its five sections (what was done · where things stand · memory updates · next steps ·
opening note). The SessionStart hook injects the newest handoff next time — this file IS the
"remember where we left off" mechanism.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 56 lines · 64 tokens per session scan A b6555f756a66
close-session is a skill published in the GitHub repository awrshift/agent-memory-kit (31 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 864 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to close-session, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
task-close-postmortem
Postmortem capture + bridge-improvement scan at task close. Surfaces six optional questions (time invested, estimate vs actual, what went well, what burned time, where the bridge fell short, concrete improvement proposal), writes structured frontmatter back to STATUS.md, and generates proposal files under…
remove-ai-flavor
Skill "remove-ai-flavor" from ItamarZand88/awesome-agent-conventions, covering 去除 ai 味道, 目标, 使用边界, 判断模式 and gotchas.
diagnose-with-memory
과거 실패 기억을 회상해 버그를 진단하고 근본원인을 다시 기억에 남길 때 사용한다.
tdd-with-memory
과거 결정·컨벤션을 회상해 테스트 우선으로 구현하고 새 컨벤션을 기억에 남길 때 사용한다.
docs
Routes one document to its Diataxis mode (tutorial, how-to guide, reference, explanation), drafts or edits it under that mode's constraints, and checks its markdown form against CommonMark 0.31.2. Use when: writing or generating documentation, deciding where a doc belongs, moving or reorganizing docs, splitting a…