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 dees91/agent-skill-manager --skill skill-advisorgit clone --depth 1 https://github.com/dees91/agent-skill-managerWrote 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/dees91/agent-skill-manager/skill-advisor)<a href="https://agentmods.dev/skills/dees91/agent-skill-manager/skill-advisor"><img src="https://agentmods.dev/badge/skills/dees91/agent-skill-manager/skill-advisor/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/dees91/agent-skill-manager/skill-advisor"><img src="https://agentmods.dev/badge/skills/dees91/agent-skill-manager/skill-advisor.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 | $0.00131 | $0.01631 |
| Opus 5.5 | $0.00052 | $0.00652 |
| Sonnet 5.5 | $0.00026 | $0.00326 |
| Haiku 4.5 | $0.00013 | $0.00163 |
Grade A, and why
skill-advisor 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 28d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Advisor
Identify only specialized local skills that materially improve the current task. Report which selected skills are already active and which need activation. Keep every activation reversible and scoped to the current Claude Code, Codex, Muse, or Grok host.
Check compatibility
- Identify the current host as
claudefor Claude Code,codexfor Codex,musefor Muse, orgrokfor Grok. Do not infer the host from repository files or a tool name mentioned by the user. Stop without mutation if the host is ambiguous. - Run
skill-manager advisor status --tool <host> --json. - Require
apiVersionto equal1andcapabilitiesto containranked_search_v1. If the command is unavailable, invalid, or incompatible, ask the user to install or update Skill Manager and continue without activating skills. Do not fall back tolist --json --query. Readprovider.mode. Cloud recommendation applies only whencapabilitiescontainssemantic_recommendation_v1andprovider.modeistypesafe; otherwise useadvisor searchexactly as before. - If any later advisor command fails with error code
STATE_VERSION_UNSUPPORTED, a newer Skill Manager has upgraded the local state. Ask the user to update Skill Manager, continue without activating skills, and do not retry.
Recommend with the configured provider
When provider.mode is typesafe and semantic_recommendation_v1 is present, send a concise task brief through stdin instead of relying on search alone:
skill-manager advisor recommend \
--tool <claude|codex|muse|grok> \
--query 'video remotion ffmpeg animation rendering' \
--task-stdin \
--json <<'BRIEF'
Build a Remotion composition and encode the rendered frames with ffmpeg.
BRIEF
Write one to five sentences, with no secrets or filesystem paths, under 8192 bytes. Never add --provider typesafe unless the user asked for that provider in this conversation. Treat recommendedSkills as suggestions the agent may reject. If outcome is none, select nothing unless clearly needed. If outcome is local_candidates, the provider was not used (fallbackReason); treat candidates like search results and do not retry.
What ships with it
1 file 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.
- 28d ago Changed · +1 lines c0ff56452f93
- 29d ago Changed · +16 lines 5ffe306761f2
- 1mo ago Changed · +3 lines · +6 tokens per session 1c544e21c651
- 1mo ago First seen · 76 lines · 125 tokens per session scan A 2107f8248883
skill-advisor is a skill published in the GitHub repository dees91/agent-skill-manager (1 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 1,631 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
web-typography
Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", "typographic scale", or "the text is hard to read". Also trigger when choosing between system…
crossing-the-chasm
Navigate the technology adoption lifecycle from early adopters to mainstream market. Use when the user mentions "crossing the chasm", "beachhead segment", "whole product", "early adopters vs mainstream", "tech go-to-market", "bowling pin strategy", "technology adoption lifecycle", "pragmatist buyers", "growth stalled…
hooked-ux
Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "habit formation", "engagement loops", "habit zone", or "the manipulation matrix". Also trigger when designing notification or re-engagement strategies, building…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…