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 martian56/claude-engineer --skill project-memorygit clone --depth 1 https://github.com/martian56/claude-engineerWrote 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/martian56/claude-engineer/project-memory)<a href="https://agentmods.dev/skills/martian56/claude-engineer/project-memory"><img src="https://agentmods.dev/badge/skills/martian56/claude-engineer/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/martian56/claude-engineer/project-memory"><img src="https://agentmods.dev/badge/skills/martian56/claude-engineer/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 | $0.00050 | $0.00539 |
| Opus 5.5 | $0.00020 | $0.00216 |
| Sonnet 5.5 | $0.00010 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
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 1mo 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
Announce at start: "I'm using claude-engineer:project-memory to keep durable project state."
Long autonomous builds outlive a single context window. Memory lives in files, not your head. The claude-engineer SessionStart hook auto-loads these at the start of every session.
The state files (in .claude-engineer/)
memory.md- durable project memory: key decisions (+ why), established conventions, the data model, open threads/risks, and "next action". The single source of truth for why things are the way they are.progress.md- the task ledger: each task with status (todo / doing / done), the commit/branch, and a one-line result. Append-only-ish; never delete history.current-phase.txt- one line naming the active phase (e.g.Phase 2 - Frontend).quality-gate-status.json- written by the project quality-gate runner; read by the commit gate. Do not hand-edit.
Iron Law
Trust the ledger and git log over your own recollection. After compaction, re-read these files before acting. Never re-run a task progress.md marks done.
When to update
- After every task: append a line to
progress.md. - On every non-obvious decision: add it to
memory.md(mirror big ones intodocs/plan/decisions.md). - On phase change: update
current-phase.txt.
Initialize (Phase 0 / planning)
Create .claude-engineer/ with seed memory.md (problem, stack, data model, decisions-so-far, next action), an empty progress.md ledger, and current-phase.txt. Add .claude-engineer/quality-gate-status.json to .gitignore (machine-generated); commit memory.md/progress.md so teammates and future sessions share them.
Red flags - STOP
- Starting work without reading
memory.md+progress.mdfirst. - A decision made in chat but never written down → write it now; chat is not durable.
- Re-deriving something already settled in
memory.md.
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.
- 1mo ago First seen · 34 lines · 50 tokens per session scan A 0765b4961343
project-memory is a skill published in the GitHub repository martian56/claude-engineer (2 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 539 once invoked, about $0.0002 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
reflect
Per-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR changes so the project stops repeating mistakes. Run periodically.
remember
Review auto-memory entries and propose promotions to CLAUDE.md, CLAUDE.local.md, or shared memory. Also detects outdated, conflicting, and duplicate entries across memory layers.
dream
Memory consolidation - review, merge, prune, and index memory files. Run periodically to keep memories organized and up-to-date.
audit-context
Measures where a project's Claude context is going before applying any of clean-context's levers. Reports what Glob discovers with and without ignore files applied, the twenty largest files in the repo and which are generated, the cumulative size of every CLAUDE.md loaded for this working directory, and how many MCP…
whats-up
Fetch recent activity from Autographical — what the user and their AI agents have been working on. Use when starting a session, when the user mentions recent activity, when the user alludes to what they were doing or looking at, or picking up where they left off. Also use when the conversation feels like a topic…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.