fire-skill

A command-line tool for managing skills: reusable instruction packages for agents. It can create, import, test, list, inspect usage, export, browse, and upgrade them.

In plain words
What is it for?
Use it to create skills from a session or summary, import them from a URL or file, validate them, view statistics, share them, or upgrade their format.
Why use it?
It puts common skill-management tasks behind one consistent command instead of requiring separate tools or manual file work.

Command

Install

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.

agentmods
npx agentmods add commands/thierryn/fire-flow/fire-skill
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,299 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.05299
Opus 5 $0.00011 $0.02649
Sonnet 5 $0.00004 $0.01060
Haiku 4.5 $0.00002 $0.00530

Measured 3d ago against content hash 56a49064d5f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fire-skill scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL "https://raw.githubusercontent.com/{owner}/{repo}/main/{path}/SKILL.md"
commands/fire-skill.md · 771 lines

How it starts

The opening of the file, as written. The whole thing — 771 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fire-skill - Unified Skill Management CLI

One command for all skill operations. Inspired by npx skills, oh-my-zsh plugins, and the Agent Skills ecosystem — but designed for Dominion Flow's security-first approach.

Subcommands

/fire-skill create [name]        Create a new skill (quick or wizard mode)
/fire-skill import [source]      Import skill from URL, file, or marketplace
/fire-skill test [name]          Validate and dry-run a skill
/fire-skill list [filter]        List skills with filtering and stats
/fire-skill stats [name]         Usage analytics for one or all skills
/fire-skill export [name]        Export skill for sharing
/fire-skill browse               Interactive skill browser with preview
/fire-skill upgrade [name]       Upgrade skill to latest template format

/fire-skill create

Quick Mode (one-liner)

# Minimal — just a name and type, fills defaults
/fire-skill create "retry-backoff" --type api-integration --category api-patterns

# From current session — auto-extracts the pattern you just solved
/fire-skill create --from session

# From a RECORD.md summary
/fire-skill create --from summary

Interactive Mode (default when no --type given)

/fire-skill create "retry-backoff"
=============================================================
              SKILL CREATION — SELECT TYPE
=============================================================

What kind of skill is this?

  1. debug-pattern       Diagnose & fix a specific bug
                         Has: symptoms, detection, elimination checklist,
                         before/after, verification steps

  2. api-integration     Connect to an external API or service
                         Has: env vars, client setup, retry/resilience,
                         webhook handling, test mocks

  3. ui-component        Reusable UI pattern or component
                         Has: wireframe, props API, responsive behavior,
                         accessibility checklist, state management

  4. architecture        Structural/design pattern
                         Has: Mermaid diagram, principles, trade-offs,
                         migration path, decision criteria

  5. devops-recipe       Infrastructure, CI/CD, deployment
                         Has: prerequisites, step-by-step, verification,
                         rollback plan, monitoring metrics

  6. general             Standard problem/solution skill
                         Has: problem, solution, code example, when to
                         use/not use (current default format)

  Select type (1-6): > _
=============================================================

Read the full file on GitHub · 771 lines

Changes

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.

  1. 3d ago First seen · 771 lines · 22 tokens per session scan A 56a49064d5f6

Subscribe to this mod's changes

fire-skill is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 20d ago), licensed MIT. It adds 22 tokens to every session and 5,299 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.