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 skills add jukrap/ai-agent-playbook --skill project-memorygit clone --depth 1 https://github.com/jukrap/ai-agent-playbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jukrap/ai-agent-playbook/project-memory)<a href="https://agentmods.dev/skills/jukrap/ai-agent-playbook/project-memory"><img src="https://agentmods.dev/badge/skills/jukrap/ai-agent-playbook/project-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jukrap/ai-agent-playbook/project-memory"><img src="https://agentmods.dev/badge/skills/jukrap/ai-agent-playbook/project-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00024 | $0.00260 |
| Opus 5 | $0.00012 | $0.00130 |
| Sonnet 5 | $0.00005 | $0.00052 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
project-memory 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 4d ago.
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.
What it actually says
Project Memory
Use the project's existing record entrypoint, such as CURRENT.md, for the active objective, constraints, next action, and links. Read only relevant records, narrowing by repository, topic, month, kind, or path where supported before expanding. Ordinary edits do not require a new worklog.
Record meaningful milestones, decisions, important findings, blockers, and handoffs. Keep current reusable facts in topic knowledge and detailed evidence in dated worklogs, using monthly folders for the new layout. Preserve existing records, ownership, source locators, and local-only rules; distinguish intended contracts, implementation, configuration, and observed behavior.
Shared workspace records apply only to explicitly registered members. Confirm the selected repository before code or Git operations; record location alone does not select a code target. Records do not require Git.
Read references/current-state.md when updating current state or resuming work. Read references/evidence-and-handoff.md for detailed evidence, handoffs, or an optional independent DRAFT. The main task normally records its own work; it reviews delegated drafts before incorporation. Native host memory is optional; ordinary files are sufficient.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · +2 lines 8f9e36976a42
- 6d ago First seen · 13 lines · 24 tokens per session scan A 7c13c73233f7
project-memory is a skill published in the GitHub repository jukrap/ai-agent-playbook (2 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 260 once invoked, about $0.0001 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 2026-09-06.
Other skills, from other repositories
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
recall-memory
Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.
agent-expert-creation
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
ac-memory-manager
Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.