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/codenamev/claude_memory/memory-first-workflownpx skills add codenamev/claude_memory --skill memory-first-workflowgit clone --depth 1 https://github.com/codenamev/claude_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 | $0.00026 | $0.00940 |
| Opus 5 | $0.00013 | $0.00470 |
| Sonnet 5 | $0.00005 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
memory-first-workflow 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 2d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory-First Research Pattern
When answering questions about code, architecture, patterns, decisions, or technical choices, follow this workflow:
Step 1: Query Memory First
Before reading files or exploring code, check if memory already has the answer:
memory.recall "<topic>"
Example queries:
memory.recall "authentication flow"memory.recall "database choice"memory.recall "error handling patterns"
Step 2: Use Specialized Shortcuts
For specific types of questions, use targeted memory tools:
Before Implementing Features
memory.decisions
Returns architectural decisions and constraints that may affect implementation.
Before Working with Frameworks/Databases
memory.architecture
Returns framework choices, database selection, and architectural patterns.
Before Writing Code
memory.conventions
Returns coding style, naming conventions, and project standards.
If Finding Contradictions
memory.conflicts
Returns open disputes that need resolution.
Step 3: Evaluate Memory Results
If memory has sufficient information:
- Answer using recalled facts
- Cite fact IDs or sources: "From memory (fact #42): ..."
- Avoid unnecessary file reads
If memory has partial information:
- Share what memory knows
- Note what needs investigation: "Memory shows we use PostgreSQL, but I need to check the connection pooling setup..."
- Proceed to file exploration for missing details
If memory has no information:
- Note explicitly: "Memory has no prior knowledge about [topic]"
- Proceed to file exploration
- After learning, consider if this should be stored in memory
Step 4: Explore Code (Only If Needed)
When memory is insufficient, use file exploration tools:
Readfor specific filesGrepfor searching contentGlobfor finding files by patternTask(Explore agent) for broad investigations
Step 5: Distinguish Sources
When presenting findings, clearly separate:
- Recalled knowledge: "From memory: We use RSpec for testing"
- Discovered information: "From code exploration: Found additional test helper in
spec/support/"
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.
- 2d ago First seen · 145 lines · 26 tokens per session scan A ac5c32457fbf
memory-first-workflow is a skill published in the GitHub repository codenamev/claude_memory (24 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 940 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 2026-08-30.
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…