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/ashishpatill/tell-proof/ship-loopnpx skills add ashishpatill/tell-proof --skill ship-loopgit clone --depth 1 https://github.com/ashishpatill/tell-proofWrote 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/ashishpatill/tell-proof/ship-loop)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/ship-loop"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/ship-loop.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 | $0.00055 | $0.00623 |
| Opus 5 | $0.00028 | $0.00311 |
| Sonnet 5 | $0.00011 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
ship-loop 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship loop
Close the loop from “open PR” to “merged on the base branch.” No vibes. No attribution noise.
Invariants
- Semantic commits only —
feat|fix|docs|test|chore|refactor(scope): summary. One concern per commit. - No attribution — do not add
Co-authored-by,Signed-off-by, or names of tools/agents/people in commit subjects or bodies. - Push every cycle —
git push -u origin <branch>after each commit batch. - Do not force-push to a shared PR branch unless the user explicitly asks.
- Merge only when green — local gates pass (
pnpm test/ typecheck / package tests). Never wait on or re-run GitHub Actions; remote CI is out of scope unless the user explicitly asks about it. - Prefer the PR that contains the work just shipped — if multiple drafts stack, merge the tip that includes the rest (or merge base then tip in order).
Loop
| Step | Action |
|---|---|
| 1. Identify | gh pr view <n> / gh pr checks <n> — branch, base, checks, review threads |
| 2. Diagnose | Local typecheck/tests, Playwright eye for UI PRs, leftover draft status — not GitHub Actions |
| 3. Fix | Smallest change that clears a named local failure |
| 4. Commit | Semantic message, no attribution trailers |
| 5. Push | Upstream the branch |
| 6. Re-check | Re-run local gates; if red, go to 2 |
| 7. Ready | Undraft if still draft |
| 8. Merge | Only if user asked (merge / merge when ready). Prefer local green over remote CI. |
Local gates (Tell)
pnpm -F @tell/design-skills test # if engine touched
pnpm -F @tell/web typecheck
pnpm test # if broader
For showcase/UI: Playwright eye on /showcase — craft beat visible, no empty right gutter, no nav-only thumbs.
Stop conditions
- Done: PR merged, branch deleted optional, working tree clean vs base.
- Blocked: Missing permissions, failing required check you cannot fix, or user-required review — report the blocker; do not fake a merge.
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.
- 4d ago First seen · 54 lines · 55 tokens per session scan A 18d7a723c407
ship-loop is a skill published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 9d ago), licensed MIT. It adds 55 tokens to every session and 623 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
animate-text
Curated text animation catalog with exact JSON specs for headings, labels, counters, and text swaps. Use when an agent needs to pick or translate named effects like soft blur in, typewriter, shared axis, line reveal, stagger, crossfade, or kinetic builds into WAAPI, Motion, Framer Motion, GSAP, CSS, Lottie, Rive, or…
better-design
Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).