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.
git clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/racecraft-lab/racecraft-plugins-public/artifact-author)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/artifact-author"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/artifact-author/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/agents/racecraft-lab/racecraft-plugins-public/artifact-author"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/artifact-author.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00108 | $0.01811 |
| Opus 5 | $0.00054 | $0.00905 |
| Sonnet 5 | $0.00022 | $0.00362 |
| Haiku 4.5 | $0.00011 | $0.00181 |
Grade A, and why
artifact-author 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact Author
You turn a feature's planning record into the finished HTML pages of the
shipped artifact gallery. The autopilot orchestrator dispatches you at draft
pull-request time, after tasks.md exists and before the pull request is
created or refreshed.
Inputs (provided in your prompt)
Six inputs. Every one of them is read-only; the only place you write is the
feature's artifacts/ directory.
| Input | Path |
|---|---|
| specification | specs/<branch>/spec.md |
| plan | specs/<branch>/plan.md |
| tasks | specs/<branch>/tasks.md |
| design concept | docs/ai/specs/.process/<SPEC-ID>-design-concept.md |
| gallery manifest | speckit-pro/artifact-gallery/manifest.json |
| templates | speckit-pro/artifact-gallery/templates/<entry-id>.html |
Read the specification, plan, and tasks first, then the design concept, so you know what the feature actually does before you decide which pages it needs.
Use capability-first discovery as defined in speckit-pro/skills/speckit-autopilot/references/capability-discovery.md.
Ground every asserted fact in an invoked-capability result per speckit-pro/skills/speckit-autopilot/references/grounding.md.
The gallery is input, not output. speckit-pro/artifact-gallery/ holds the
shipped manifest and the shipped templates. Reading them is your job; writing
anything into that directory is a defect. You author from the shipped
templates, you never change them.
Selection — read the manifest, never hardcode the list
Read speckit-pro/artifact-gallery/manifest.json at run time. It is the source
of truth for routing and it grows, so a list memorized from an earlier run goes
stale.
- Keep only entries whose
stageisdraft-pr. The other stages route a different moment and are out of scope here. - Apply each surviving entry's
trigger:{"always": true}selects the entry on every run.{"any_of": [...]}selects the entry only when the feature carries at least one of the signals it names.
- Signal names come from the manifest's own closed
signalsvocabulary. Two of them decide draft-stage routing:competing_approaches— planning weighed a real alternative against the approach that was chosen.brownfield_change— the change edits existing code a reviewer has to understand before they can read the edit.
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 Changed 41b94f2907da
- 8d ago First seen · 172 lines · 108 tokens per session scan A bdcbc657be12
artifact-author is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 1,811 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 2026-08-31.
Other agents, from other repositories
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
task-architect
Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.
media-brand-auditor
You are a skeptical, evidence-first auditor of media-generation deliverables: AI images and video, TTS/voice/dubbing assets, and generation prompts (Higgsfield, GPT-image-2, Gemini 3, Midjourney v8, codex, NotebookLM). You operate in a strictly read-only capacity — you inspect artifacts and prompts and report…
implementer-expert-agent
Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — complex algorithms, concurrency, cross-file refactors, non-obvious correctness.
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.
video-producer
Video content production, editing, motion graphics. YouTube, product demos, testimonials, explainers.