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 instructions/caphtech/pce-memory/agents-mdgit clone --depth 1 https://github.com/CAPHTECH/pce-memoryWhat 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 | $0.03566 | $0.03566 |
| Opus 5 | $0.01783 | $0.01783 |
| Sonnet 5 | $0.00713 | $0.00713 |
| Haiku 4.5 | $0.00357 | $0.00357 |
Grade A, and why
pce-memory AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pce-memory とは
プロジェクトの知識(設計決定、規約、好み、タスク)を永続化し、セッションを跨いで想起するためのMCPサーバーです。
利用フロー
1. activate → タスク開始前に intent-aware な想起を行う(topology walk で関連 claim を自動展開)
2. observe → 会話ログ・作業メモ・機密を raw micro memory として一時記録
3. distill → raw 観測を durable 候補に蒸留
4. promote → reviewable candidate を meso/macro memory に昇格
5. feedback → 想起した知識の有用性をフィードバック
6. rollback → 無効になった durable memory を append-only で修復(topology-based blast radius 付き)
7. link_claims → claim 間のリンク作成(supports/extends/contradicts/supersedes/related)
8. graph_audit → knowledge graph の健全性監査(orphan/cycle/scope hole/hub 検出)
upsert は already-distilled な durable knowledge の escape hatch としてのみ使ってください。通常の raw -> durable 変換経路では使いません。
いつ activate するか
以下の状況で pce_memory_activate を呼び出してください:
- 新しいタスクを開始するとき - 関連する過去の決定を確認
- 設計判断が必要なとき - 既存のアーキテクチャ決定を参照
- 命名や規約を確認したいとき - プロジェクト固有のルールを想起
- エラーに遭遇したとき - 過去の類似問題の解決策を検索
// 例: API設計前に関連知識を想起
{
"intent": "design_decision",
"q": "API 命名規約 RESTful",
"scope": ["project", "principle"],
"kind_filter": ["fact", "preference", "policy_hint"],
"memory_type_filter": ["knowledge", "procedure", "norm"],
"allow": ["answer:task"],
"top_k": 10
}
いつ observe するか
以下の情報は pce_memory_observe で記録してください:
- session スコープの作業文脈 - 「このファイルを編集中」「デバッグ中の仮説」
- 生ログや一時メモ - チャット断片、ツール出力、HTTPレスポンス、ファイル読み取り結果
- secret/PII を含む可能性がある内容 - fail-safe に一時保存し、durable claim 化しない
// 例: セッション作業メモを一時記録
{
"source_type": "chat",
"content": "Issue #65 の observe 互換経路を削除中"
}
補足:
observeは raw-only です。durable claim を inline で作成しませんsingle_claim_v0のような旧 extraction mode は使いませんextract: { \"mode\": \"noop\" }は互換性のために残っていても raw-only のままです- durable 化したい場合は
distill -> promoteを使ってください
いつ upsert するか
以下の情報だけを pce_memory_upsert で記録してください:
- すでに distill 済みとみなせる durable knowledge
projectまたはprincipleに置くべき確定事項- provenance を付けて追跡可能にしたい事実・好み・手順・ポリシー
- 技術・ファイル・概念の関係が明確な場合は、
entities/relationsも同じupsertに含めてください
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 · 367 lines · 3,566 tokens per session scan A a9767c5200bd
pce-memory AGENTS.md is an instructions file published in the GitHub repository CAPHTECH/pce-memory (3 stars, last pushed 5mo ago), licensed MIT. It adds 3,566 tokens to every session, about $0.0178 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.