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 compactable-tool-whitelist-gatinggit 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/compactable-tool-whitelist-gating)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/compactable-tool-whitelist-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/compactable-tool-whitelist-gating/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/compactable-tool-whitelist-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/compactable-tool-whitelist-gating.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 | $0.00029 | $0.00420 |
| Opus 5 | $0.00015 | $0.00210 |
| Sonnet 5 | $0.00006 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
compactable-tool-whitelist-gating 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 9d 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: Compactable Tool Whitelist Gating
Domain: microcompaction
Trigger: Apply when cache-editing compacts conversation transcripts and must avoid deleting outputs from tools that cannot be safely re-run or are non-text.
Source Pattern: Distilled from reviewed session memory, compaction, and context-budgeting implementations.
Core Method
Define a fixed set of safe tools whose outputs can be trimmed via cached microcompact. Compose the set from shell tools, file read/write utilities, grep/glob/web fetch/search, and optionally other text-generating helpers. The microcompact path consults this set to decide whether to register a tool result for deletion, so no unsupported or stateful tools ever get silently mutated.
Key Rules
- Build the whitelist as a static
Setonce so permission checks stay fast and deterministic. - Include only tools whose outputs are recoverable or purely text (shell commands, grep/glob, file read/write, fetch/search, etc.).
- Skip tools not on the list so cache edits never attempt to delete specialized state (APIs that mutate files, image tools, etc.).
- Document that new tools must be evaluated before being added to the whitelist to avoid breaking reads.
- Keep the set close to the microcompact path and highlight it in comments so the gating logic stays obvious.
Example Application
When cached microcompact inspects assistant messages, it only registers tool uses whose names appear in compactable tools, ensuring the summarizer never tries to delete non-text or stateful outputs like MCP connectors or tool search metadata.
Anti-Patterns (What NOT to do)
- Do not treat all tools equally—many produce binary or stateful outputs that cannot be safely recompiled from cache edits.
- Do not mutate the whitelist at runtime; it must remain a static, vetted guardrail for cached compaction.
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.
- 9d ago First seen · 29 lines · 29 tokens per session scan A 2a97680d076c
compactable-tool-whitelist-gating is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 420 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
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.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
ackit-context-optimization
Build budgeted context packs and trim instruction bloat for coding agents.
chain
Inject the 3 most recent session IDs for the current workspace into the prompt before Claude responds. Use when starting work and wanting recent session context.
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
k-knowledge
Instructions for recording stable project facts in AGENTS.md or a project map. AGENTS.md is a file that stores guidance for coding agents.