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/umputun/cc-thingz/execnpx skills add umputun/cc-thingz --skill execgit clone --depth 1 https://github.com/umputun/cc-thingzWhat 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 | $0.00041 | $0.07217 |
| Opus 5 | $0.00020 | $0.03608 |
| Sonnet 5 | $0.00008 | $0.01443 |
| Haiku 4.5 | $0.00004 | $0.00722 |
Grade A, and why
exec 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 yesterday.
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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
exec
Execute plan file tasks sequentially, each in an isolated subagent.
Arguments
$ARGUMENTS— path to plan file (optional; if omitted, ask user to pick fromplans_diruserConfig directory, default:docs/plans/)
File Resolution
ALWAYS use the resolve script to read prompt and agent files. NEVER construct the override chain manually:
bash ${CLAUDE_PLUGIN_ROOT}/skills/exec/scripts/resolve-file.sh prompts/task.md ${CLAUDE_PLUGIN_DATA}
bash ${CLAUDE_PLUGIN_ROOT}/skills/exec/scripts/resolve-file.sh agents/quality.txt ${CLAUDE_PLUGIN_DATA}
The script checks project overrides, user overrides, and bundled defaults automatically.
Placeholder Substitution
After reading a prompt file, replace ALL placeholders with actual values before passing to a subagent. Subagents run in fresh contexts without plugin env vars.
Always substitute: PLAN_FILE_PATH, PROGRESS_FILE_PATH, DEFAULT_BRANCH, ${CLAUDE_PLUGIN_ROOT} (resolve to actual absolute path), RESOLVE_SCRIPT (absolute path to ${CLAUDE_PLUGIN_ROOT}/skills/exec/scripts/resolve-file.sh), PLUGIN_DATA_DIR (resolved ${CLAUDE_PLUGIN_DATA} path — passed as second argument to resolve-file.sh so it can find user overrides), USER_RULES (resolved custom rules content from the rules loading step, or empty string if no rules found), and phase-specific values (FINDINGS_LIST, REVIEW_PHASE, DIFF_COMMAND).
Custom Rules Loading
Before starting execution, run this command via Bash tool to check for user-provided custom rules:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/resolve-rules.sh planning-rules.md ${CLAUDE_PLUGIN_DATA}
If the output is non-empty, store it as the resolved custom rules content. When substituting USER_RULES in task prompts, wrap the content with a label so the subagent understands it: use "ADDITIONAL CUSTOM RULES:\n" as the substitution. If the output is empty, substitute an empty string for USER_RULES. See ${CLAUDE_PLUGIN_ROOT}/references/custom-rules.md for full documentation on the rules mechanism.
What ships with it
24 files 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.
- references/agents/documentation.txt 1.3 KB
- references/agents/implementation.txt 1.2 KB
- references/agents/quality.txt 1.6 KB
- references/agents/simplification.txt 2.3 KB
- references/agents/smells.txt 1.8 KB
- references/agents/testing.txt 1.5 KB
- references/prompts/codex-review.md 1.4 KB
- references/prompts/finalizer.md 2.4 KB
- references/prompts/fixer.md 2.9 KB
- references/prompts/progress-file.md 1.8 KB
- references/prompts/review.md 6.3 KB
- references/prompts/stats.md 4.2 KB
- references/prompts/task.md 4.6 KB
- scripts/append-progress.sh 539 B runs code
- scripts/create-branch.sh 5.3 KB runs code
- scripts/customize-file.sh 4.0 KB runs code
- scripts/detect-branch.sh 1.9 KB runs code
- scripts/detect-vcs.sh 410 B runs code
- scripts/init-progress.sh 451 B runs code
- scripts/move-plan.sh 1.3 KB runs code
- scripts/resolve-file.sh 1.4 KB runs code
- scripts/run-codex.sh 1.8 KB runs code
- scripts/run-external-review.sh 3.4 KB runs code
- scripts/stage-and-commit.sh 2.6 KB runs code
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.
- yesterday First seen · 307 lines · 41 tokens per session scan A 62ca4eb287f7
exec is a skill published in the GitHub repository umputun/cc-thingz (460 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 7,217 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
plugin-publish
发布 Zhin.js 插件到 npm 和 Zhin 插件市场。Use when asked to publish a plugin, prepare for release, check publish readiness, or submit to the Zhin plugin marketplace. 引导完成发布前检查、版本管理和提交流程。.
smalltalk-commenter
Generates and improves CRC-style (Class-Responsibility-Collaborator) class comments for Smalltalk/Tonel classes. Use whenever lint (st-lint) flags a class as missing or having a poor class comment, when the user asks to "add class comments", "document classes in [package]", "check class documentation", or after…
smalltalk-debugger
Systematic debugging guide for Smalltalk (Pharo/Squeak) development. Provides expertise in error diagnosis (MessageNotUnderstood, KeyNotFound, SubscriptOutOfBounds, AssertionFailure), incremental code execution with eval tool, intermediate value inspection, error handling patterns (on:do: blocks), stack trace…
smalltalk-developer
Comprehensive Smalltalk (Pharo/Squeak) development workflow guide with AI-driven Tonel editing. Provides expertise in Tonel file format syntax (class definitions with name, superclass, instVars, category, method categories, class comment placement), package structure (package.st placement, directory organization…
smalltalk-usage-finder
Class and method usage analyzer for Smalltalk (Pharo/Squeak). Provides expertise in understanding class responsibilities through class comments (getclasscomment), discovering usage patterns via references (searchreferencestoclass), finding example methods (exampleXXX patterns), analyzing method usage in context…
smalltalk-implementation-finder
Method implementation finder and analyzer for Smalltalk (Pharo/Squeak). Provides expertise in discovering implementors across class hierarchies (searchimplementors), analyzing implementation patterns, learning coding idioms from existing implementations, assessing refactoring impact (counting implementors and…