TÂCHES Claude Code Resources is a collection of custom commands, skills, and agents that structure Claude Code workflows such as planning, debugging, automation, and subagent creation. It is intended for developers who use Claude Code for real software projects. The catalogue entries are examples of the resources included in the collection.
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.
git clone --depth 1 https://github.com/glittercowboy/taches-cc-resourcesWrote 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/commands/glittercowboy/taches-cc-resources/run-prompt)<a href="https://agentmods.dev/commands/glittercowboy/taches-cc-resources/run-prompt"><img src="https://agentmods.dev/badge/commands/glittercowboy/taches-cc-resources/run-prompt/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/commands/glittercowboy/taches-cc-resources/run-prompt"><img src="https://agentmods.dev/badge/commands/glittercowboy/taches-cc-resources/run-prompt.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 | $0.00019 | $0.01402 |
| Opus 5 | $0.00010 | $0.00701 |
| Sonnet 5 | $0.00004 | $0.00280 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
run-prompt 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 11d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Single prompt:
- Empty (no arguments): Run the most recently created prompt (default behavior)
- A prompt number (e.g., "001", "5", "42")
- A partial filename (e.g., "user-auth", "dashboard")
Multiple prompts:
- Multiple numbers (e.g., "005 006 007")
- With execution flag: "005 006 007 --parallel" or "005 006 007 --sequential"
- If no flag specified with multiple prompts, default to --sequential for safety
<step2_resolve_files> For each prompt number/name:
- If empty or "last": Find with
!ls -t ./prompts/*.md | head -1 - If a number: Find file matching that zero-padded number (e.g., "5" matches "005-.md", "42" matches "042-.md")
- If text: Find files containing that string in the filename
<matching_rules>
- If exactly one match found: Use that file
- If multiple matches found: List them and ask user to choose
- If no matches found: Report error and list available prompts </matching_rules> </step2_resolve_files>
<step3_execute> <single_prompt>
- Read the complete contents of the prompt file
- Delegate as sub-task using Task tool with subagent_type="general-purpose"
- Wait for completion
- Archive prompt to
./prompts/completed/with metadata - Commit all work:
- Stage files YOU modified with
git add [file](nevergit add .) - Determine appropriate commit type based on changes (fix|feat|refactor|style|docs|test|chore)
- Commit with format:
[type]: [description](lowercase, specific, concise)
- Stage files YOU modified with
- Return results </single_prompt>
<parallel_execution>
- Read all prompt files
- Spawn all Task tools in a SINGLE MESSAGE (this is critical for parallel execution): Use Task tool for prompt 005 Use Task tool for prompt 006 Use Task tool for prompt 007 (All in one message with multiple tool calls)
- Wait for ALL to complete
- Archive all prompts with metadata
- Commit all work:
- Stage files YOU modified with
git add [file](nevergit add .) - Determine appropriate commit type based on changes (fix|feat|refactor|style|docs|test|chore)
- Commit with format:
[type]: [description](lowercase, specific, concise)
- Stage files YOU modified with
- Return consolidated results </parallel_execution>
<sequential_execution>
- Read first prompt file
- Spawn Task tool for first prompt
- Wait for completion
- Archive first prompt
- Read second prompt file
- Spawn Task tool for second prompt
- Wait for completion
- Archive second prompt
- Repeat for remaining prompts
- Archive all prompts with metadata
- Commit all work:
- Stage files YOU modified with
git add [file](nevergit add .) - Determine appropriate commit type based on changes (fix|feat|refactor|style|docs|test|chore)
- Commit with format:
[type]: [description](lowercase, specific, concise)
- Stage files YOU modified with
- Return consolidated results </sequential_execution> </step3_execute>
<context_strategy> By delegating to a sub-task, the actual implementation work happens in fresh context while the main conversation stays lean for orchestration and iteration. </context_strategy>
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.
- 11d ago First seen · 167 lines · 19 tokens per session scan A 9b126f2c94f6
run-prompt is a command published in the GitHub repository glittercowboy/taches-cc-resources (1,976 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 1,402 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 commands, from other repositories
organize
Sort, group, and clean up import statements across the project.
t00-compact
A command that switches replies into an extremely short mode, removing filler and keeping only conclusions, code, numbers, errors, and pending decisions.
report
Generate a project analytics report covering code quality, velocity, and health metrics.
explain
Explain a code file, function, or concept in clear, structured language.
document-all
Auto-document the entire codebase by generating module-level docs, function signatures, and API references.
write-post
Write a technical blog post with a clear structure, code examples, and actionable takeaways.