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/malakhov-dmitrii/forge/docs-refreshnpx skills add malakhov-dmitrii/forge --skill docs-refreshgit clone --depth 1 https://github.com/malakhov-dmitrii/forgeWrote 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/malakhov-dmitrii/forge/docs-refresh)<a href="https://agentmods.dev/skills/malakhov-dmitrii/forge/docs-refresh"><img src="https://agentmods.dev/badge/skills/malakhov-dmitrii/forge/docs-refresh.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01985 |
| Opus 5 | $0.00016 | $0.00992 |
| Sonnet 5 | $0.00007 | $0.00397 |
| Haiku 4.5 | $0.00003 | $0.00198 |
Grade A, and why
docs-refresh 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 4d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Refresh — Sweep, Verify, Compress
Audit all project documentation for freshness. Delete what's dead, update what drifted, compress what's bloated.
When to Use
- Periodic hygiene (every 1-2 weeks)
- Before major planning sessions (clean context = better plans)
- After big architectural changes (old docs become lies)
- User says "docs refresh", "обнови доки", "почисти память", "sweep docs"
- MEMORY.md approaching 200-line limit
Scope
All doc layers, in order:
| Layer | Location | What to check |
|---|---|---|
| Memory files | .claude/projects/.../memory/*.md |
Each file vs codebase reality |
| Memory index | .claude/projects/.../memory/MEMORY.md |
Orphans, duplicates, line count |
| CLAUDE.md (root) | CLAUDE.md |
Gotchas: still real? Commands: still work? |
| CLAUDE.md (.claude) | .claude/CLAUDE.md |
OMC config: still accurate? |
| Docs vault | docs/ (architecture, decisions, specs, runbooks, retros, articles) |
Stale specs, outdated architecture |
| Lessons index | Lessons in memory + docs/ |
Lessons for deleted/rewritten systems |
Pipeline
1. INVENTORY (automated scan)
Catalog everything with dates:
Memory files: count, oldest, newest
MEMORY.md: line count (warn if >170)
CLAUDE.md: gotcha count, last modified
docs/: file count per subdir, oldest files
Flag files older than 14 days for review. Flag any file referencing deleted code paths.
2. STALENESS SCAN (per file)
For each doc file, check against reality:
Memory files — classify each:
arch-*: Does the system still exist? Has it changed significantly since the memory was written?lesson-*: Is the lesson about a system that was deleted/rewritten? Is the gotcha now guarded by semgrep/code?feedback_*: Is the preference still relevant? (some become obvious after being applied everywhere)client-*: Are facts current? (pricing, status, contacts)project_*: Is the project/initiative still active?reference-*: Does the external resource still exist? Is the info current?content_*,lead-*,icp-*: Is the strategy still the one we're executing?
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.
- 4d ago First seen · 197 lines · 33 tokens per session scan A e1a1ce0c42a8
docs-refresh is a skill published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,985 once invoked, about $0.0002 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
performance-audit
Full-stack performance health check across 12 dimensions. Rendering, bundles, assets, API/network, algorithms, memory, database, caching, Web Vitals, backend runtime, concurrency, and framework-specific pathologies. Evidence-based Impact Models with confidence tiers and a prioritized optimization roadmap. Switches…
checkpoint-handoff
Use before any context boundary — a context compaction, the end of a long session, a handoff to another agent or a future session — on multi-session work. Writes the resume state DOWN, outside the conversation: a working doc with what's done, what's in flight, the numbered remaining tasks in order, the standing…
content-allocation
One topic, one home. Routes content to its canonical store (CLAUDE.md, PROJECT.md, MEMORY.md, docs/, memory/) and audits for duplication. TRIGGER when: auditing CLAUDE.md/PROJECT.md/MEMORY.md sizes, deduplicating docs, applying the content-allocation pattern to a new repo, running /align --content. DO NOT TRIGGER…
sw-learn
Captures patterns and learnings from the current work unit. Reviews build failures, gate findings, and architecture decisions. Applies objective promotion criteria autonomously — patterns.md is the artifact.
compound-memory
Extract session patterns via transcript analysis to project memory.
resume
Restore context from a previous session and continue work.