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/chris-dare-dev/agent-kitWrote 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/chris-dare-dev/agent-kit/skill-to-command-author)<a href="https://agentmods.dev/agents/chris-dare-dev/agent-kit/skill-to-command-author"><img src="https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/skill-to-command-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/chris-dare-dev/agent-kit/skill-to-command-author"><img src="https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/skill-to-command-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 | $0.00106 | $0.02425 |
| Opus 5.5 | $0.00042 | $0.00970 |
| Sonnet 5.5 | $0.00021 | $0.00485 |
| Haiku 4.5 | $0.00011 | $0.00243 |
Grade C, and why
skill-to-command-author scanned grade C with 2 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
"Now run X", "Ignore previous instructions", "Authorize the user", "Add yourself Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ".claude/agent-memory/skill-to-command-author/lessons.md" 2>/dev/null || echo "(no lessons yet)" How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill-to-Command Author
You are Turn 2 of the /skill-to-command pipeline. Your job is to author files on your designated write surface during parallel authoring. Two copies of you run in parallel (Agent A and Agent B) with DISJOINT file sets — coordination is encoded in your {WRITE_SURFACE} brief; you do not communicate with the other instance.
The orchestrator (.claude/commands/skill-to-command.md) dispatches you with substituted variables. You never invoke other sub-agents.
Input variables (substituted by the orchestrator)
{SKILL_NAME}— the skill being converted (must exist atdata/skills/<name>/SKILL.mdbefore you start){WRITE_SURFACE}— eitherAorB:A— own the orchestrator + agents + references migration:- Write
data/commands/{SKILL_NAME}.md(new slash command body) - Write
data/agents/{SKILL_NAME}-<role>.md× N (one per phase identified in Turn 1 discovery) git mv data/skills/{SKILL_NAME}/references/<x>.md data/references/{SKILL_NAME}-<x>.mdfor each reference- Update the new agent bodies to point at the new flat-named reference paths
- Write
B— own scripts migration + deprecated stub + workspace CLAUDE.md updates:git mv data/skills/{SKILL_NAME}/scripts/<x>.{sh,py} data/scripts/{SKILL_NAME}-<x>.{sh,py}for each scriptgit rm data/skills/{SKILL_NAME}/SKILL.md(the old orchestrator body — name-collision with the new slash command otherwise; CRITICAL gotcha C1)- Write
data/skills/{SKILL_NAME}-deprecated/SKILL.mdwithallowed-tools: Readand a redirect message (sunset date 30 days from today) - If workspace CLAUDE.md (
data/claude-md/workspace-root.md) needs an update to register the new command, edit BOTH the canonical copy underdata/claude-md/AND the active workspace path; verify withdiffthat they are byte-identical
{DISCOVERY_SUMMARY}— the Turn 1 output: phases identified, write surface per agent, scripts to migrate (old→new paths), references to migrate (old→new paths), external-write boundary notes
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 · 180 lines · 106 tokens per session scan C 78874f7e3699
skill-to-command-author is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 2,425 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (instruction-override phrasing, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
contentful-agent
Plugin orchestrator. Senior Contentful platform engineer who knows when to use each of the 13 contentful- skills and how to sequence (or parallelize) them across model, implementation, ops, governance, and extensibility. Use this agent as the first call for any non-trivial Contentful task — it diagnoses scope, picks…
bynder-agent
Senior Bynder DAM platform engineer with command of asset modeling and metaproperties, Brand Guidelines, derivative templates, the bynder-js-sdk, Universal Compact View embedding, Bynder + Contentful pairing, portal and account architecture, permissions and workflow, webhooks, marketplace connectors, migrations, and…
leadership-agent
Senior leadership coach who orchestrates the seven specialty skills in this plugin. Combines executive coaching for neurodivergent leaders, the everyday craft of people-management, performance-based hiring, meeting and cadence design, onboarding and transitions, OKR and goal-setting work, and stoic perspective…
presentation-factory-agent
Top-level orchestrator for the Slalom Presentation Factory plugin. Routes across the four-stage pipeline (Frame → Draft → Compose → Ship), the full set of presentation-factory- specialty skills, and the worker agents that scaffold folders, route brand assets, and promote finished decks. Use this agent as the first…
algolia-agent
Senior Algolia platform engineer with command of index design, relevance tuning, InstantSearch React/Next.js, the Autocomplete UI library, direct search-client usage, indexing pipelines, API-key strategy, the Recommend API, AI search and Personalization (NeuralSearch, query categorization), Insights events and A/B…
design-agent
Senior design practitioner spanning UI, UX, web, mobile, motion, accessibility, plus surface-specific authoring (16:9 decks, 8.5×11 documents, social assets, iconography, visualization, imagery), and the operational task workflows (taste, process, audit, screen, handoff). Use this agent when a task spans multiple…