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/samibs/skillfoundryWrote 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/samibs/skillfoundry/quick)<a href="https://agentmods.dev/commands/samibs/skillfoundry/quick"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/quick/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/samibs/skillfoundry/quick"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/quick.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 | $0.00000 | $0.01296 |
| Opus 5.5 | $0.00000 | $0.00518 |
| Sonnet 5.5 | $0.00000 | $0.00259 |
| Haiku 4.5 | $0.00000 | $0.00130 |
Grade A, and why
quick scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
"child_process.exec(" # shell injection surface How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/quick — Lightweight Feature Workflow
Role: Minimal-ceremony feature workflow for solo developers and small changes. Implement → test → commit. No PRD required, no full pipeline overhead.
Usage
/quick "description" Implement, test, and commit a small feature
/quick "description" --challenge Add evaluator challenge (optional)
/quick "description" --no-commit Implement and test, skip commit
When to use
- Solo developer, informal feature request
- Small improvements (a flag, a config option, a new utility function)
- Prototyping before formalizing into a PRD
- Dark mode toggle, UI tweaks, non-critical additions
When NOT to use
- Production auth, payments, security-critical features → use
/feature - Multi-story features → use
/forge - When you need the full evaluator + docs pipeline → use
/feature
The Pipeline
/quick "add dark mode toggle to settings page"
STEP 1: IMPLEMENT Coder builds it (TDD when test scope is clear)
STEP 2: TESTLOOP Tests run, fixes loop until green (max 3 iterations)
STEP 3: COMMIT Scoped commit [ADVISORY if no shell]
Optional (--challenge flag only):
STEP 2.5: CHALLENGE Evaluator grades. Fix brief loops back to coder.
No shadow tester. No Anvil gates. No layer-check. No docs stage (code-level comments only). No security audit.
Behavior
Step 1: Implement
Coder reads the description and implements:
- If test scope is obvious (function, endpoint, component) → TDD: test first
- If test scope is unclear (UI tweak, config change) → implement then test
- Banned patterns still apply (no TODO, STUB, hardcoded secrets)
- No formal story scaffolding required
Step 2: TestLoop
Run /testloop with reduced settings:
/testloop --max 3 [auto-detected scope]
Max 3 iterations (vs. 5 in full /feature). If not converging after 3, report failures and stop — no further auto-fix. User decides next action.
Step 2.5: Challenge (optional, --challenge flag only)
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 · 181 lines · 0 tokens per session scan A 260c27ab1643
quick is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,296 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
fix-tests-execute
Phase 2 of fixing-tests: Fix Execution - investigate, classify, fix, verify, and commit each work item.
verify
Run verification commands and confirm output before making success claims. Use before committing, creating PRs, or claiming work is complete. Evidence before assertions, ALWAYS.
autotask
Execute development task autonomously from description to PR-ready - handles implementation, testing, and git workflow without supervision.
work-flow-feature
Complete workflow for developing a new feature, from exploration to merge.
ccc-verify
Verify the current codebase in a fixed order (build, types, lint, tests with coverage, secrets, debug logs, git status) and return a PASS/FAIL report with a ready-for-PR verdict. Use before committing, before opening a PR, or when asked to check that everything still works.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.