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 2233admin/design-pipeline --skill client-revisionsgit clone --depth 1 https://github.com/2233admin/design-pipelineWrote 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/2233admin/design-pipeline/client-revisions)<a href="https://agentmods.dev/skills/2233admin/design-pipeline/client-revisions"><img src="https://agentmods.dev/badge/skills/2233admin/design-pipeline/client-revisions/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/2233admin/design-pipeline/client-revisions"><img src="https://agentmods.dev/badge/skills/2233admin/design-pipeline/client-revisions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.02615 |
| Opus 5 | $0.00048 | $0.01307 |
| Sonnet 5 | $0.00019 | $0.00523 |
| Haiku 4.5 | $0.00010 | $0.00262 |
Grade A, and why
client-revisions 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 6d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client Revisions
Control revision rounds and scope creep on motion projects: define what a revision is, cap rounds in the SOW, collect feedback the right way, translate vague notes into actionable changes, and decline out-of-scope work politely as a change order.
When to use
Use when feedback is mounting, when a client keeps adding "small tweaks," when the SOW needs revision language, when a vague note ("make it pop") needs decoding before touching the file, or when a request has clearly crossed into new work and needs a change-order reply.
Decision tree — classify every note before touching the file
The whole skill is one judgment applied per note: is this a revision, a new request, or just vague? Run each note through this before opening the project.
A note arrives.
├─ Is it vague ("make it pop", "feels off")?
│ └─ YES → translate to a decidable choice + ask for a timestamp.
│ Do NOT act yet. Re-classify once it's concrete.
└─ Is it concrete?
├─ Does it change something ALREADY approved in brief/board?
│ (timing, palette colour, approved-copy edit, a fix)
│ └─ YES → REVISION. Counts against the round cap. Do it.
└─ Is it anything NOT in the approved brief/board?
(new scene, +runtime, new concept, new ratio, new asset,
reversing an approved decision, "let's also try…")
└─ YES → NEW REQUEST. Send the change-order email. Quote it.
Do NOT silently absorb it.
Is feedback scattered across people/messages?
└─ YES → STOP. Send the consolidated-feedback request first; one
document, all stakeholders, conflicts resolved by the client.
Decision rule: when unsure whether a note is a revision or new request, ask "was this decided and approved already?" If yes → revision. If it adds, replaces, or reverses → new request.
The core distinction: revision vs new request
This single line prevents most disputes — put it in the SOW and the feedback request:
- A revision = a change to something that was already in the approved brief/board (adjusting timing, colour from the palette, swapping an approved word, fixing a glitch).
- A new request = anything not in the approved brief/board (a new scene, added second of runtime, a different concept, a new aspect ratio, a logo not previously supplied, "let's also try…").
What ships with it
4 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.
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.
- 6d ago First seen · 206 lines · 96 tokens per session scan A ee9f29d5f81d
client-revisions is a skill published in the GitHub repository 2233admin/design-pipeline (9 stars, last pushed 6d ago), licensed MIT. It adds 96 tokens to every session and 2,615 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
contribution-workflow
Create or document a contribution workflow for a design system — the multi-stage process for evaluating, accepting, and shepherding new contributions through to publication. Trigger when someone says: how should someone contribute, contribution process, adding a new component, contribution guidelines, what's the…
backlog-generator
Transform audit findings into sprint-ready work items with effort estimates, acceptance criteria, and stakeholder-friendly rationale. This converts existing findings into tickets, NOT the process for contributing new components to the system. Trigger when someone says: generate backlog items, create tickets from…
html-ppt-knowledge-arch-blueprint
OpenDesign's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.
ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
ss-reference
Compile screenshots, URLs, Figma exports, or an existing UI into a project-local StyleSeed output grammar with evidence, tokens, confidence, anti-patterns, and a validation screen. Use when the user supplies a design reference that StyleSeed does not already model.