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 45ck/skill-harness --skill developer-artifact-shapergit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/developer-artifact-shaper)<a href="https://agentmods.dev/skills/45ck/skill-harness/developer-artifact-shaper"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/developer-artifact-shaper/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/45ck/skill-harness/developer-artifact-shaper"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/developer-artifact-shaper.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 | $0.00024 | $0.00406 |
| Opus 5.5 | $0.00010 | $0.00162 |
| Sonnet 5.5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
developer-artifact-shaper 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 1mo 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
Developer Artifact Shaper
Use this skill when a task needs a plan, design note, investigation, review report, or handoff artifact.
Core Rule
Pick the artifact format from the job it must do:
- Markdown or TOON for canonical source, git diffs, CLI/TUI handoff, and long-lived docs.
- HTML for generated human review surfaces, dense comparisons, visual diagrams, prototypes, dashboards, or desktop app previews.
- Dual when a durable source and a rich review surface are both useful.
- Model review artifacts use durable text sources and generated static review views; do not make rendered diagrams the only source.
- Product, business, data, research, UX, and mockup artifacts use visual-source-first pairs when humans need visual inspection: agent-readable source plus generated visual review surface.
- High-fidelity is the default for UI, customer-facing workflow, product, and mockup review. Low-fidelity sketches are scratch only unless explicitly captured as evidence.
Do not make generated HTML the only durable source for a decision.
Process
- Identify the artifact purpose: decision, plan, investigation, review, report, runbook, product brief, business case, data definition, research synthesis, UX flow, handoff, or prototype.
- Identify the canonical source location.
- Decide the review surface: markdown, html, or dual.
- Name the evidence that must be linked.
- For visual artifacts, choose the family: product, business, data, research, or UX.
- Decide whether the artifact should be listed in
docs/artifacts/artifacts.manifest.json. - State the update rule: edit source first, regenerate review surface second.
Output
Artifact Type
Canonical Source
Review Surface
Artifact Family
Evidence Links
Manifest Entry
Update Rule
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.
- 1mo ago First seen · 43 lines · 24 tokens per session scan A 34a0d8037f3c
developer-artifact-shaper is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 406 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
harness-init-runner
Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use aios-long-running-harness instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.
do-it-audit
Use when the user explicitly requests a deep repository or scoped audit; not for ordinary diff review.
do-it-skill-authoring
Use when creating or revising a do-it skill, its description, references, or specialist delegation guidance so it adds needed judgment without prescribing ceremony.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.