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/ilyagorsky/memory-toolkit/docs-reflectnpx skills add IlyaGorsky/memory-toolkit --skill docs-reflectgit clone --depth 1 https://github.com/IlyaGorsky/memory-toolkitWhat 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 | $0.00027 | $0.01074 |
| Opus 5 | $0.00014 | $0.00537 |
| Sonnet 5 | $0.00005 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
docs-reflect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/docs-reflect — Session knowledge → repo documentation
Collect DOC: notes accumulated during the session, generalize them into rules, and propose documentation for the repository.
Step 1: Collect findings
Two sources: DOC: notes from the current session, and recurring feedback from memory.
1a: DOC: notes
node "$MEM" --dir="$MEM_DIR" docs
1b: Recurring feedback patterns
node "$MEM" --dir="$MEM_DIR" recurring
This scans feedback/ files for clusters — similar corrections that appeared 2+ times across sessions. Recurring patterns are strong candidates for promotion to .claude/rules/.
Combine
If both sources are empty — tell user "No documentation findings." and stop.
If recurring patterns found (3+ occurrences) — these are project conventions, not personal preferences. Treat them as DOC automatically:
- Save as DOC note:
node "$MEM" --dir="$MEM_DIR" note "DOC: <domain> — <generalized rule from recurring feedback>" - Highlight to user: "This feedback appeared N times — promoting to project rule."
Patterns with 2 occurrences — mention as candidates but don't auto-promote.
Step 2: Generalize
For each DOC: note, extract a generalized rule.
Bad (too specific):
"The PaymentService bug was on line 42 in processRefund()"
Good (pattern):
"Refund operations must check transaction state before mutating — stale state causes double-refunds"
Bad (class-level):
"UserService.getProfile() returns null when user is not found"
Good (convention):
"Services return null for missing entities instead of throwing — callers must handle null"
If a note can't be generalized — skip it.
Step 3: Detect documentation structure and route
3a: Detect existing structure
ls .claude/rules/ 2>/dev/null
cat CLAUDE.md 2>/dev/null | head -50
ls docs/ 2>/dev/null
Check memory for saved preference:
node "$MEM" --dir="$MEM_DIR" search "docs_target"
3b: Choose target
If no saved preference and no .claude/rules/ directory — ask:
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.
- 3d ago First seen · 167 lines · 0 tokens per session scan A b6bc52cd0ddd
docs-reflect is a skill published in the GitHub repository IlyaGorsky/memory-toolkit (13 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 1,074 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
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
math-unicode
Use when a response needs mathematical notation (equations, filters, set-builder notation, statistics, calculus, linear algebra, logic, ratios, drops, counts) and the output goes to a terminal or TUI that cannot render LaTeX: Claude Code, Codex CLI, SSH and tmux sessions, CI logs. Load it before composing, including…
vibe-ship
Generates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.yml, .dockerignore, CI/CD (GitHub Actions), scalability config (health checks, resource limits, K8s on request), and security hardening (non-root user, secrets, dependency scanning). Auto-detects the stack…
anatomia-cc
ES: Te dice qué construir en Claude Code y te da el esqueleto de archivos: skill y en qué modo, subagente, hook, servidor MCP, plugin, rutina, artefacto, app con el Agent SDK, una línea en CLAUDE.md, o nada. Corré esto antes del primer archivo. Se dispara con «esto lo hago como skill o como agente», «necesito un MCP o…
create-agents-md
Create concise, repository-specific AGENTS.md files with operational contract, precedence rules, and drift-control guidance.
create-checkpoint
Capture the current session state as a checkpoint artifact per spec section 4.4. Use when the user signals session end or explicitly requests a checkpoint. Do not use mid-session or without user approval.