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 me-cedric/agent-compass --skill project-memorygit clone --depth 1 https://github.com/me-cedric/agent-compassWrote 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/me-cedric/agent-compass/project-memory)<a href="https://agentmods.dev/skills/me-cedric/agent-compass/project-memory"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/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/me-cedric/agent-compass/project-memory"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/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 | $0.00035 | $0.00349 |
| Opus 5.5 | $0.00014 | $0.00140 |
| Sonnet 5.5 | $0.00007 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
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 10d 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
Before work
pjm regenerate # after a pull or merge: fold the shared events of teammates into the log
pjm brief
pjm precheck
For a non-trivial task, also search the memory for the files, modules, libraries and errors that the task touches.
Shared and local
events.jsonl is the committed source of truth. It merges as a union.
The projections (summary.md, PROJECT_MAP.md, AI_INSTRUCTIONS.md, issues/) are git-ignored. pjm regenerate rebuilds them.
Never commit a projection. A committed summary overwrites the work of teammates.
During work
Log each of these when it happens:
- A failed attempt.
- An important finding.
- A fragile file or a risky area.
- A library or tooling gotcha that other people can reuse.
After work
Log these items:
- Decisions and fixes.
- Files changed.
- Validation commands and their results.
- Remaining risks.
Write a committed ADR in {{ADR_DIR}} for each durable architecture decision. Use the skill adr. One file for each decision merges cleanly.
Never log
- Secrets, tokens or credentials.
- Personal data or raw customer data.
- Temporary brainstorming.
If projectmem is not available, continue the task. Report memory logging as not run, with the reason.
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.
- 10d ago Changed · -18 lines · -7 tokens per session ab7f55207196
- 1mo ago First seen · 72 lines · 42 tokens per session scan A b2ec4302bb4f
project-memory is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 349 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
wiki-ingest
Use when an operation issue asks to ingest a captured raw/ source into the LLM Wiki, or the user says "ingest ". Create durable source, entity, concept, synthesis, index, and log pages; use paperclip-distill for Paperclip bundles.
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
memory-context
Load relevant long-term memory from Hindsight before starting work. Use at the start of every task or request, before planning or answering, and whenever the user mentions people, projects, decisions, preferences or anything done before.
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.