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 fmind/agent-supagents --skill use-agent-supagentsgit clone --depth 1 https://github.com/fmind/agent-supagentsWrote 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/fmind/agent-supagents/use-agent-supagents)<a href="https://agentmods.dev/skills/fmind/agent-supagents/use-agent-supagents"><img src="https://agentmods.dev/badge/skills/fmind/agent-supagents/use-agent-supagents/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/fmind/agent-supagents/use-agent-supagents"><img src="https://agentmods.dev/badge/skills/fmind/agent-supagents/use-agent-supagents.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 | $0.00044 | $0.00679 |
| Opus 5.5 | $0.00018 | $0.00272 |
| Sonnet 5.5 | $0.00009 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
use-agent-supagents 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 22d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Supagents
Read compatibility evidence for tested host versions and limits. Read usage and configuration for target paths, precedence, and migration rules. Use Supagents to share role instructions while keeping model, tool, and permission settings explicit for each harness.
Workflow
- Inspect existing sources, generated outputs, Git status, and installed harness versions. Preserve handwritten profiles and unrelated work.
- Select project (
.agents/supagents/) or global (~/.agents/supagents/) scope. Usesupagents init NAME --project --target claude --target codexto scaffold selected targets; adapt the target list to the installed hosts. - Write a bounded role: task inputs, responsibilities, allowed actions, handoff format, and stop conditions. Read the relevant host's current documentation before setting native metadata.
- Keep shared
nameanddescriptionfields and the Markdown body portable. Put model choices, tool allowlists, permissions, and other host settings in their target blocks. Omit model overrides unless requested or required by the task. - Preview with
supagents build --project --diff; inspect warnings and output mappings. For custom layouts pass--source-dir PATH --config FILEconsistently. - Generate with
supagents build --project --strict; verify expected and obsolete outputs withsupagents check --project --strict. Invalid source/configuration, collisions, and unowned outputs must be fixed before generating. - Confirm native discovery in each installed host, then run a bounded runtime task when authorized. Report compilation, discovery, and runtime results separately.
Native formats
AGY,CLAUDE,COPILOT,CURSOR,GEMINI,GROK,KILO, andOPENCODEemit Markdown with merged YAML frontmatter.CODEXemits TOML and stores the shared body plusAPPEND_BODYasdeveloper_instructions; do not declare that field separately. Supply nonemptynameanddescriptionstrings.OUTPUToverrides a file path. Relative overrides resolve beside the source; configured project directories resolve from the working directory.- Custom targets can select
format: tomland abody_key; Supagents does not translate native fields or validate complete harness schemas.
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.
- 22d ago Changed · -78 lines · -9 tokens per session scan B → A b93fe1826325
- 1mo ago First seen · 113 lines · 53 tokens per session scan B d6cc16b6ce1e
use-agent-supagents is a skill published in the GitHub repository fmind/agent-supagents (6 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 679 once invoked, about $0.0002 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
generate-package-skill
Generate or update an Agent Skill that teaches consumers one npm or local package the user maintains, including framework modules and wrappers. Tests each example against the installed version. Use when a maintainer asks for a package Skill, a SKILL.md for their library, or a Skill update after a release.
generate-project-skill
Generate or update an Agent Skill from the observed workflows, boundaries, and conventions of one software project.
skilld-tui-design
Designs and verifies skilld CLI output, terminal pickers, and full-screen flows. Use for terminal colours, loading feedback, keyboard controls, layout, errors, or end-to-end CLI UX reviews.
update-package-skill
Updates an existing package Skill for a new release of its npm or local package by testing only what changed since the version the Skill names. Use when a maintainer asks to refresh a package Skill after a release, or when a SKILL.md names an older tested version than the package.
review-skill
Review an Agent Skill for valid structure, clear triggers, usable instructions, current evidence, and risky or unclear actions.
skilld
Operate skilld CLI for Skill discovery, use, installation, inspection, updates, authentication, configuration, restoration, and removal, including Repository, curator, and collection refs. Also read the skilld.dev registry (view, browse, trending, tracks, curators, index) and act for the user's skilld.dev account…