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 ychampion/cskill-agents --skill role-aware-context-slimminggit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/role-aware-context-slimming)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/role-aware-context-slimming"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/role-aware-context-slimming/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/ychampion/cskill-agents/role-aware-context-slimming"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/role-aware-context-slimming.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 | $0.00033 | $0.00481 |
| Opus 5.5 | $0.00013 | $0.00192 |
| Sonnet 5.5 | $0.00007 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
role-aware-context-slimming 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 1mo 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.
What it actually says
SKILL: Role-Aware Context Slimming
Domain: context-management
Trigger: When an agent declares omitClaudeMd or runs as an Explore/Plan helper, slim the context before handing it to runAgent.
Source Pattern: Distilled from reviewed context, compaction, and memory-governance patterns.
Core Method
Use the omitClaudeMd flag (and the tengu_slim_subagent_claudemd feature gate) to strip claudeMd from the user context unless an override was explicitly provided. For read-only helpers such as Explore or Plan, drop the gitStatus entry from the system context because it is stale and bloats the payload. Always compute new context objects instead of mutating the originals so other agents can still read the full metadata set.
Key Rules
- Only remove
claudeMdwhenagentDefinition.omitClaudeMdis true, no user override is present, and the feature flag allows it, so you do not throw away intentional user context edits. - Derive
userContextNoClaudeMdby destructuring the base context and omittingclaudeMdbefore assigningresolvedUserContext. - Drop
gitStatusfromresolvedSystemContextany timeagentDefinition.agentTypeisExploreorPlan, while leaving other system keys intact. - Preserve the original contexts for the parent agent so they can continue to see the full metadata when needed.
Example Application
When the CLI launches an Explore subagent, apply this skill to create resolvedUserContext without claudeMd and resolvedSystemContext without gitStatus, saving dozens of tokens and preventing stale git information from confusing the helper.
Anti-Patterns (What NOT to do)
- Stripping
claudeMdeven though the caller supplied an override user context; that override often carries explicit corrections or clarifications. - Forgetting to remove
gitStatusfor Explore/Plan agents, which bloats the prompt with stale files and slows down the API call.
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.
- 1mo ago First seen · 28 lines · 33 tokens per session scan A 9690bd8835bb
role-aware-context-slimming is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 481 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log, then draft only the root pages that have meaningful content and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.