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/lixiansenqwq/classmap-skill/classmap-maintainnpx skills add LIXianSenQwQ/classmap-skill --skill classmap-maintaingit clone --depth 1 https://github.com/LIXianSenQwQ/classmap-skillWrote 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/lixiansenqwq/classmap-skill/classmap-maintain)<a href="https://agentmods.dev/skills/lixiansenqwq/classmap-skill/classmap-maintain"><img src="https://agentmods.dev/badge/skills/lixiansenqwq/classmap-skill/classmap-maintain.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 | $0.00086 | $0.00927 |
| Opus 5 | $0.00043 | $0.00464 |
| Sonnet 5 | $0.00017 | $0.00185 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
classmap-maintain 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
classmap-maintain
Maintain CLASSMAP.md: a lightweight, human-readable code responsibility map for AI coding sessions.
The goal is to help future agents locate the right classes, modules, components, services, controllers, repositories, hooks, stores, APIs, and tests without broad repository search.
Core Rule
Prefer reading code over asking the user.
Ask only when code and existing docs cannot resolve an important ambiguity. If code and CLASSMAP.md disagree, trust code and update CLASSMAP.md.
Responsibilities
Use this skill to:
- Create
CLASSMAP.mdwhen it does not exist. - Repair stale, incomplete, or inaccurate entries.
- Add important newly discovered code units.
- Mark unclear or mixed responsibilities instead of guessing.
- Preserve useful manual notes unless they contradict code.
- Keep the map useful for future AI coding tasks.
Do not:
- Implement feature changes.
- Rewrite unrelated business code.
- Turn
CLASSMAP.mdinto a glossary. - Put domain terminology explanations in
CLASSMAP.md; useCONTEXT.md. - Put architecture decisions in
CLASSMAP.md; usedocs/adr/or design docs. - Put task plans, PRDs, issue text, or source-code dumps in
CLASSMAP.md.
Workflow
-
Inspect existing context:
CLASSMAP.mdCODEMAP.mdCONTEXT.mdREADME.mddocs/- package/module structure
-
Detect the project shape:
- frontend, backend, full-stack, library, monorepo
- main frameworks
- source directories
- test directories
- generated, vendor, dependency, and build directories to ignore
-
Build or update the map:
- Start from high-level features and entrypoints.
- Identify important code units, not every tiny helper.
- For each code unit, capture ownership, non-ownership, dependencies, callers, related tests, and change triggers.
- Ground every entry in code or existing docs.
-
Keep edits scoped:
- For a missing map, create a useful first version.
- For a stale map, prefer accurate targeted updates over broad speculative rewrites.
- For unclear ownership, mark uncertainty explicitly.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 139 lines · 86 tokens per session scan A 556b99530038
classmap-maintain is a skill published in the GitHub repository LIXianSenQwQ/classmap-skill (3 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 927 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
chronicle-skysight
Use when recent Linux desktop activity memory would help answer a question or when the user asks to inspect or control Chronicle or Skysight.
echo
Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.