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 craigcossairt/trellis --skill launch-checkgit clone --depth 1 https://github.com/craigcossairt/trellisWrote 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/craigcossairt/trellis/launch-check)<a href="https://agentmods.dev/skills/craigcossairt/trellis/launch-check"><img src="https://agentmods.dev/badge/skills/craigcossairt/trellis/launch-check.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00530 |
| Opus 5 | $0.00028 | $0.00265 |
| Sonnet 5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
launch-check 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 8d 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
You are running a pre-demo audit. This ensures the app is presentable for user interviews, investor pitches, or a launch.
Audit Steps
1. Test Data Cleanup
Check for and flag any test/dev artifacts that would look unprofessional:
- Search for hardcoded test emails, phone numbers, or names in the codebase
- Search for
TODO,FIXME,HACK,XXXin screens/pages that are part of the demo flow - Check for debug print/log statements in production code paths
grep -rn "TODO\|FIXME\|HACK\|XXX" <source-dir> | head -20
grep -rn "console\.log\|debugPrint\|print(" <source-dir> | head -20
2. Critical Screen Audit
Review each screen in the demo flow for polish (no layout overflow, no missing states):
- Entry point (splash / landing / login)
- Core flow screen 1
- Core flow screen 2
- Settings / profile
3. Error State Coverage
For each critical screen, verify:
- Empty state exists and is user-friendly (not blank or an error)
- Network error handling (what happens offline?)
- Loading states (skeleton/spinner, not blank white)
4. Brand Consistency
- Brand colors used consistently
- Correct fonts for headings and body
- Logo displays correctly
- No default framework placeholder icons visible
5. Static Analysis
# FILL IN: your lint/typecheck command, e.g. `npm run lint` or `flutter analyze`
Output Format
Produce a report with:
- PASS items (confirmed good)
- WARN items (minor, won't break the demo but should fix)
- FAIL items (must fix before demo)
End with a prioritized fix list for any FAIL items.
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.
- 8d ago First seen · 66 lines · 55 tokens per session scan A 86caf53550a5
launch-check is a skill published in the GitHub repository craigcossairt/trellis (4 stars, last pushed 18d ago), licensed MIT. It adds 55 tokens to every session and 530 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
lov-fix-until-no-error
A verification-focused debugging workflow that repeatedly runs specified checks, fixes the highest-priority failure, and stops when the checks pass or a genuine external blockage remains.
template-formal
Strongly-typed multiagent ant-robot colony exemplar — ADTs, session-typed protocols, affine-discipline resource handles, storage-as-functor framing, Active-Inference-flavored decision loop, mypy-as-oracle negative controls.
template-reproducibility-audit
Deterministic reproducibility audit — fixed seeds, regenerate-from-clean, double-run diff before Zenodo/arXiv/release. USE WHEN outputs drift between runs, "worked on my machine", need regenerate-from-clean proof, or pre-release reproducibility check — even without naming docs/prompts.
template-test-creation
Create pytest suites under the no-mocks policy — real data, temp files, subprocess, pytest-httpserver. USE WHEN adding tests, raising coverage, testing new src/ module, or user forbids mocks.
infrastructure-benchmark
Deterministic benchmark harnesses for public template exemplars. Use when scoring generated project outputs against benchmark manifests, refreshing the default template smoke manifest, checking publication-readiness rubrics, or adding bounded no-network readiness checks for public template outputs.
infrastructure-sia
Skill for the Self-Improvement Agent (SIA) harness contract. Use when validating task public/private layouts, generation artifact trees, evaluation runners, fixture replay loops, or opt-in live Meta→Target→Feedback cycles in template projects.