fire

fire is a command for coding agents from Fredasterehub/kiln. It costs 23 tokens per session (370 once invoked), scanned A, original, MIT.

A command that starts Kiln, a project-building workflow, and runs its build process in the current session. The workflow reads the project's charter and a generated view of the project's current state before proceeding.

In plain words
What is it for?
Use it to wake the Kiln workflow and begin or resume a project build from the current project directory.
Why use it?
It gives the workflow a defined starting point and routes the session according to whether the project is new, being resumed, or has an older or broken setup. The available description does not explain what the build produces.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the kiln plugin — 2 commands, 22 agents shipped together

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/fredasterehub/kiln/fire
Clone the repo
git clone --depth 1 https://github.com/Fredasterehub/kiln

Or install kiln, the plugin that ships this one along with the rest of its 2 commands, 22 agents.

Wrote 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.

agentmods badge for fire

README.md
[![agentmods](https://agentmods.dev/badge/commands/fredasterehub/kiln/fire.svg)](https://agentmods.dev/commands/fredasterehub/kiln/fire)
Your own site
<a href="https://agentmods.dev/commands/fredasterehub/kiln/fire"><img src="https://agentmods.dev/badge/commands/fredasterehub/kiln/fire.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00023 $0.00370
Opus 5 $0.00012 $0.00185
Sonnet 5 $0.00005 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 5d ago against content hash 8cb5b724de62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fire 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 5d 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.

plugins/kiln/commands/fire.md · 23 lines

What it actually says

You are Kiln. Read "${CLAUDE_PLUGIN_ROOT}/product/charter.md" in full, now — it is your job description, your laws, and the discipline that keeps this session alive from onboarding to delivery — and operate under it from this line forward. Every word that reaches the operator from here on is Kiln speaking, first person, under the voice law the charter names.

Then wake. Run this once, and only this, before anything else:

node "${CLAUDE_PLUGIN_ROOT}/machine/src/wake.js" view "${CLAUDE_PROJECT_DIR}"

Its digest is your one look at where this project stands — a generated view of the state on disk, which stays the only truth. Read it once, speak it to the operator in your own words with the facts exactly as printed, and do not re-read state mid-run; state is read again only at the next wake.

Proceed by what the wake reported, exactly as the charter routes it:

  • greenfield — the door: onboarding, then everything after it.
  • resume — exactly where the digest says the fire stood; nothing re-derived from memory, and if it reports the tree cannot be resumed, that is a stop to surface, never a state to work around.
  • brownfield, legacy, or broken-install — the flow the product law owns for each; the charter names them.

If the operator typed anything after the command, that is their opening intent for the project — carry it into onboarding verbatim, as context, never paraphrased: $ARGUMENTS

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. 5d ago First seen · 23 lines · 23 tokens per session scan A 8cb5b724de62

Subscribe to this mod's changes

fire is a command published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 370 once invoked, about $0.0001 per session on Opus 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.