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 skills add LIXianSenQwQ/classmap-skill --skill classmap-targetgit 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-target)<a href="https://agentmods.dev/skills/lixiansenqwq/classmap-skill/classmap-target"><img src="https://agentmods.dev/badge/skills/lixiansenqwq/classmap-skill/classmap-target/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lixiansenqwq/classmap-skill/classmap-target"><img src="https://agentmods.dev/badge/skills/lixiansenqwq/classmap-skill/classmap-target.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00063 | $0.00946 |
| Opus 5.5 | $0.00025 | $0.00378 |
| Sonnet 5.5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
classmap-target 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 14d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
classmap-target
Use CLASSMAP.md to choose candidate code, then verify its responsibilities in the current source.
The result should explain where to look first and any boundary that matters to the request. Locating responsible code does not by itself establish a bug's root cause.
Scope
- Requests limited to location, explanation, analysis, or review are read-only, including the map. Report any drift without repairing it.
- Continue into implementation only when the user requests it, following the project's normal coding workflow. This skill adds routing guidance, not a separate implementation process.
- During implementation, synchronize an existing map only under the incremental rule below and within the user's authorized scope.
- Creating or broadly refreshing a map belongs to
classmap-maintainwhen requested. Do not make it a prerequisite for the current task.
Workflow
- Identify the requested behavior and useful clues, such as a feature name, symptom, route, event, or symbol. Distinguish a location-only request from an implementation request.
- If the user supplied a specific file or symbol, start there and consult the map as useful. Otherwise, read relevant parts of
CLASSMAP.mdto select candidates. If the map is missing, briefly say so and use focused search for this task; do not create it. - Read candidate code before presenting a recommendation. Verify the paths and responsibilities, following relevant entrypoints or callers where needed. Trust code over the map and state any remaining uncertainty.
- If the candidates do not explain the behavior, expand search as described below.
- Output a concise, verified routing note. For a location-only request, stop after the recommendation and any verification limits. For implementation, continue with the requested change, then consider a scoped map update.
Search When Needed
An absent map entry is not evidence that the behavior is absent from the project.
Follow relevant entrypoints, callers, and implementations; search within the likely module, then use repository-wide targeted search if the location is still unresolved. Use request clues and code evidence as search terms. Skip a narrower step when there is no useful module or candidate to start from.
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.
- 14d ago Changed · -78 lines · -28 tokens per session 4e5b4baa56f6
- 2mo ago First seen · 142 lines · 91 tokens per session scan A 304499184ac2
classmap-target is a skill published in the GitHub repository LIXianSenQwQ/classmap-skill (5 stars, last pushed 13d ago), licensed MIT. It adds 63 tokens to every session and 946 once invoked, about $0.0003 per session on Opus 5.5. 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
guide
Show a quick-reference guide for all Token Pilot tools — when to use each one.
stats
Show Token Pilot session analytics — token savings, per-tool breakdown, top files, per-agent grouping.
install
Install or check ast-index binary (auto-downloads if missing).
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…