Borrowing it
Nothing to install: this file belongs to adrienm7/ergopti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adrienm7/ergopti/main/.agents/skills/project-memory/SKILL.mdgit clone --depth 1 https://github.com/adrienm7/ergoptiWrote 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/adrienm7/ergopti/project-memory)<a href="https://agentmods.dev/skills/adrienm7/ergopti/project-memory"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/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/adrienm7/ergopti/project-memory"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/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 | $0.00023 | $0.00598 |
| Opus 5.5 | $0.00009 | $0.00239 |
| Sonnet 5.5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
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 15d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project memory
docs/memory/README.md is the routing index for hard-won knowledge. The actual
entries live beside it in focused files under docs/memory/.
docs/PROJECT_MEMORY.md is only a compatibility pointer for older clients.
This catalog is shared by every developer, agent and reviewer and replaces
agent-private memory stores.
Consult it first
Read docs/memory/README.md, then only the topic files covering the area you
will touch. Do not load every topic by default. A meaningful share of "new"
bugs in this repo are documented recurrences.
What belongs here
Something non-obvious, durable, and written in English: a foot-gun that cost real debugging time, an invariant that is not visible from the code, a decision whose rationale would otherwise evaporate, an intentional asymmetry that looks like a bug.
What does not belong: anything the repo already records — code structure, the
content of a fix (that is the commit), git history, or universal rules already
written in AGENTS.md. Do not restate; link instead.
Entry format
Add the entry to the narrowest existing topic file.
### slug-with-dashes
One concise paragraph naming the mechanism and the action future work must take.
Use dash-separated slug headings. Keep entries short enough to scan and link directly to code/tests when that is more useful than restating them.
Writing well
- Be concrete. "Guard the map access" is useless; name the file, the key, the failure mode, and what the symptom looked like.
- Convert relative dates to absolute. "Last week" is meaningless in six months.
- Record the symptom, not just the cause — that is the string a future reader searches for when they hit it again.
- Check for an existing entry first and extend it rather than adding a near duplicate. Delete entries that turn out to be wrong.
- Delete stale history. Completed audit transcripts, branch narratives, commit summaries, temporary measurements, and TODO snapshots belong in Git, not project memory.
- Verify before trusting. Entries reflect what was true when written. If one names a file, function or flag, confirm it still exists before acting on it — and correct it if not.
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.
- 15d ago First seen · 65 lines · 23 tokens per session scan A b724d0f9ea43
project-memory is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 598 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 2026-10-14.
Other skills, from other repositories
context-map
Generates a compressed project context map to avoid expensive Read/Grep calls. Use at session start or before implementing features in an unfamiliar codebase.
Context Manager
Manage conversation context and memory for optimal AI performance.
Performance Optimizer
Systems-level performance engineer: identifies hotspots, provides optimized code with resource justifications.
auto-context
An automatic context detector that identifies the files, functions, and other code context an AI needs for a task.
performance-optimizer
A performance improvement assistant that analyses applications, identifies bottlenecks, and suggests ways to make them faster.
context-engineering
Use this skill for optimizing AI context windows. Covers context sizing, prioritization, and avoiding context overflow.