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/iamk77/skill/pilotnpx skills add IamK77/Skill --skill pilotgit clone --depth 1 https://github.com/IamK77/SkillWhat 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 | $0.00236 | $0.03065 |
| Opus 5 | $0.00118 | $0.01533 |
| Sonnet 5 | $0.00047 | $0.00613 |
| Haiku 4.5 | $0.00024 | $0.00307 |
Grade A, and why
pilot 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 2d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pilot
A harbor pilot doesn't repaint your ship — they board it because they know these waters, and put you on
the right course through them. pilot is the front door to the atelier suite: it takes a design task, a
goal, or just "this looks bad and I can't say why", and returns a routing verdict — run this lens, enter
the design system at this layer, run these in order, redirect to a sibling suite, or don't reach for a
skill, here's why. It is a dispatcher, not a method, so it has no GATEs; its whole value is the call it
makes in the next paragraph, not a flight plan it walks you through.
Earn your keep above the harness, or stay quiet. The harness already routes a single clearly-named
task to its skill on the trigger description alone. So pilot exists for the five things matching can't do:
- Enter at the right layer — design is a system built in layers, and most design work is not a blank
canvas. The single highest-value call here is "your build works but it reads cheap → the problem is the
color system and the type scale, start at
color/type, not a full redesign." Don't make someone define a whole design language when their work enters at one layer. - Sequence — "make it look premium" is really several lenses in order; name the chain (
canon→color→type→layout→form→motion→systems) and the hand-offs, and which to skip. - Redirect — within design (the confusable lenses below) and across suites: the mechanism of CSS
is
surface:keel, what to build issurface:bearings, general code craft isengineering:plumb. This is the highest-value routing and the one a trigger match never does. - Refuse — the honest "no skill for this" (a one-off throwaway, a single color tweak). A router that always finds a lens to sell is worse than none.
- Disambiguate — the confusable calls (
canonvscoloron "the palette";layoutvssurface:keelon "the grid";formvsgraphicson "the visual";systemsvssurface:bulwarkon "the design system") where the wrong pick wastes a flight plan.
Scope: the eight atelier lenses only — and atelier owns the look and feel, not all of frontend. How
the CSS cascade / Grid / Flexbox actually work is surface:keel — atelier owns the composition
judgment, keel owns the mechanism. What to build, the user's mental model, and whether a design is
manipulative is surface:bearings. State, data, the unhappy paths, accessibility, and the performance
budget are surface (wellspring / seaworthy / lookout). General code craft, architecture, testing,
process, and security are engineering. Realtime/offline correctness is distributed. Choosing a
library is quarry. Point there; don't absorb.
What ships with it
3 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.
- 2d ago First seen · 183 lines · 236 tokens per session scan A 5e5621c54c4b
pilot is a skill published in the GitHub repository IamK77/Skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 236 tokens to every session and 3,065 once invoked, about $0.0012 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
quick-recap
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.