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 skills/severity1/claude-code-auto-memory/memory-processornpx skills add severity1/claude-code-auto-memory --skill memory-processorgit clone --depth 1 https://github.com/severity1/claude-code-auto-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 | $0.00057 | $0.01140 |
| Opus 5 | $0.00028 | $0.00570 |
| Sonnet 5 | $0.00011 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
memory-processor 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Processor
Process changed files and update relevant memory file sections (CLAUDE.md or AGENTS.md, whichever is the active file per project config) following official guidelines.
Guidelines
MANDATORY: All rules below must be followed exactly. Violations produce incorrect CLAUDE.md content.
@../shared/references/guidelines.md
Algorithm
-
Parse context: Read context provided by memory-updater agent:
- Changed files with categories
- File content summaries
- Detected dependencies
- Git context (commits, diffs)
- Target memory files (CLAUDE.md or AGENTS.md per project config)
-
Categorize changes: Map files to CLAUDE.md sections using the tables in "Section Names" below. Match changed files to their update triggers.
-
Analyze impact: Determine what needs updating:
- New build commands added?
- Architecture changed (new dirs, renamed components)?
- New coding patterns detected?
- Dependencies added/removed?
-
Verify and update content: Before modifying documented content, verify accuracy:
Key distinction - conventions vs patterns:
conventions: Explicit rules humans decided (naming, imports, formatting)patterns: Implicit patterns AI detected from recurring code structures
Removal verification:
- Read the relevant CLAUDE.md section to get currently documented items
- For each item that appears missing from changed files:
- Use Grep to search the codebase for that item
- Search in relevant directories excluding node_modules, vendor, .git
- If item exists elsewhere: keep it documented
- If item is not found anywhere: mark for removal
Stale command detection:
- Compare documented commands against commands that actually executed successfully
- If documented command differs from successful execution, update to match what worked
- Examples:
- Documented:
python pytest| Actually worked:python -m pytest→ Update - Documented:
npm test| Actually worked:npm run test→ Update - Documented:
pytest tests/| Actually worked:uv run pytest→ Update
- Documented:
- Source: Successful Bash tool executions from session context or git commit history
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 · 122 lines · 57 tokens per session scan A dfbfa3deb3a1
memory-processor is a skill published in the GitHub repository severity1/claude-code-auto-memory (157 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,140 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…