Borrowing it
Nothing to install: this file belongs to TheSmokeDev/taskchad-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheSmokeDev/taskchad-os/master/.claude/skills/clutch/SKILL.mdgit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/thesmokedev/taskchad-os/clutch)<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/clutch"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/clutch/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/thesmokedev/taskchad-os/clutch"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/clutch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 254 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 543 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Excessive Agency · line 432 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00081 | $0.07770 |
| Opus 5 | $0.00041 | $0.03885 |
| Sonnet 5 | $0.00016 | $0.01554 |
| Haiku 4.5 | $0.00008 | $0.00777 |
Grade A, and why
clutch 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 10d 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 — 732 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLUTCH v3 Orchestrator
Claude Layered Unified Team Coordination Hub — Resilient Multi-Phase Orchestration with Pre/Post-Build Adversarial Review
Arguments: $ARGUMENTS
Parse arguments using this logic:
PRD Path Mode (first argument ends with .md)
If the first argument ends with .md, it's a direct path to a PRD file:
PRD_PATH- Direct path to the PRD filePROJECT_PATH- Derived by going up from PRDs/ folderSTART_PHASE- Second argument (default: 1)END_PHASE- Third argument (default: auto-detect from PRD)
Project Path Mode
If the first argument does NOT end with .md:
PROJECT_PATH- Absolute path to project (default: current working directory)START_PHASE- Second argument (default: 1)END_PHASE- Third argument (default: 4)PRD_PATH- Auto-discover fromPROJECT_PATH/PRDs/folder
Detection Logic
If $ARGUMENTS[0] ends with ".md":
PRD_PATH = $ARGUMENTS[0]
PROJECT_PATH = dirname(dirname(PRD_PATH))
START_PHASE = $ARGUMENTS[1] or 1
END_PHASE = $ARGUMENTS[2] or auto-detect from PRD
PRD_NAME = basename without extension
Else:
PROJECT_PATH = $ARGUMENTS[0] or current working directory
START_PHASE = $ARGUMENTS[1] or 1
END_PHASE = $ARGUMENTS[2] or 4
PRD_PATH = auto-discover from PROJECT_PATH/PRDs/
PRD_NAME = discovered PRD basename
Adversarial Mode (v3)
CLUTCH v3 adds an --adversarial flag with three values:
| Mode | Pre-build (Step 1c) | Post-build (Step 5a) | Use case |
|---|---|---|---|
--adversarial=no |
skip | skip | Trivial phases (legacy v2 behavior) |
--adversarial=yes (default) |
R1 + revise + R2 + greenlight gate | one round of diff review | Standard phases |
--adversarial=aggressive |
R1 + revise + R2; if REJECT, R3 + revise + R4 | up to 2 fix-loop rounds | High-stakes (security, schema migrations, framework foundations) |
If command -v codex returns non-zero, CLUTCH falls back to --adversarial=no for the affected phase with a warning.
Mode Detection
What ships with it
15 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.
- assets/post-build-adversarial-template.md 4.3 KB
- assets/prp_base.md 8.3 KB
- assets/r1-adversarial-template.md 4.5 KB
- assets/r2-adversarial-template.md 4.2 KB
- assets/revise-template.md 2.2 KB
- assets/workflow-template.md 2.1 KB
- references/adversarial-review.md 9.4 KB
- references/codebase-analysis.md 4.5 KB
- references/create-prd.md 5.6 KB
- references/execute-prp.md 2.9 KB
- references/generate-prp.md 7.8 KB
- references/piv-discovery.md 3.8 KB
- references/prd-exemplar-slack-threads.md 6.4 KB
- references/team-coordinator-contract.md 8.1 KB
- references/team-orchestration.md 14 KB
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.
- 10d ago First seen · 732 lines · 81 tokens per session scan A df4e82f49a75
clutch is a skill published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 7,770 once invoked, about $0.0004 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
dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
atmos-modernization
Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.
atmos-workflows
Workflow automation: native step types, multi-step workflows, parallel/matrix/wait/container/emulator steps, when: conditions (CEL), require/assert preconditions, output steps, retries, dependencies, and cross-component orchestration.
atmos-imports
Atmos imports: local and remote stack imports, go-getter schemes, templated imports, import context, remote imports vs component source/vendoring, and private GitHub imports through github/sts.
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.
task-forest
Maintains a repo-local task forest or task DAG for the current workspace. Use when the user asks to initialize or update a task forest, close a session, summarize evolving project work, align a request with a global goal, track progress/history/deviations/todos, save or apply a task proposal, or export the…