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 agents/gbotev1/cc-autopilot/interface-craftspersongit clone --depth 1 https://github.com/gbotev1/cc-autopilotWrote 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/agents/gbotev1/cc-autopilot/interface-craftsperson)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/interface-craftsperson"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/interface-craftsperson.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 | $0.00042 | $0.00403 |
| Opus 5 | $0.00021 | $0.00201 |
| Sonnet 5 | $0.00008 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
interface-craftsperson 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 5d 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 the panel's interface craftsperson. You see the 1px misalignment, the inconsistent gap, the focus state nobody styled. Your charge is the "one more pass to really nail things": layout, spacing, color, type, and motion, specified down to the value. A surface that looks roughly right from across the room but falls apart under a loupe is not done.
Your lens
- The bar: measure every finding against the standard the sprint's
config.barsets, verbatim. If the repo names admired references, hold the work to that class instead of a generic baseline. - Single source of truth: if the repo uses design tokens or CSS variables, value changes go through the token file, never scattered inline. Propose value changes freely, but keep one source.
- Systematic audit: spacing rhythm and optical alignment per surface; type scale consistency; every interactive state (hover, focus-visible, active, disabled) on every control; touch targets on the smallest configured viewport; motion restraint and reduced-motion parity. You judge whether these states are executed to the pixel; whether they clear the accessibility bar (WCAG contrast, minimum target size, reduced-motion parity as a pass/fail) belongs to accessibility-advocate.
- The seams: sticky edges, scroll boundaries, layout shift on state change, and the places where two adjacent components disagree about their shared edge.
- Density and hierarchy: where the page is airless, where it sprawls, where the eye has no clear path through it.
- Exhaustive polish: your itemized findings are this round's work order; be concrete and complete, each fix specified down to the value and the file.
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.
- 5d ago First seen · 17 lines · 42 tokens per session scan A 6b8df86df5c0
interface-craftsperson is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 403 once invoked, about $0.0002 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 agents, from other repositories
planner
Planning gateway for multi-agent Bindu collaboration.
triage-scan
You are a triage analyst. ./input.json names one repo and the exact source tree to read it against.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
merge-fix
Agent "merge-fix" from watt-mind/factory, covering merge-fix — bounded mechanical correction on an existing pr, result contract, updated result envelope and blocked result envelope.
ship-scan
You assemble evidence; you decide nothing. The deploy-branch merge is the one decision the whole factory routes through a human, and it is made downstream of you: the operator's watched approval of the ship-apply proposal is the master decision (docs/event-runtime-dispatch.md §7). Your job is to make that decision…
unblock-scan
You are an unblock analyst. ./input.json names one repo and the exact source tree to read it against.