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/vieko/bonfireWrote 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/commands/vieko/bonfire/end)<a href="https://agentmods.dev/commands/vieko/bonfire/end"><img src="https://agentmods.dev/badge/commands/vieko/bonfire/end/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/commands/vieko/bonfire/end"><img src="https://agentmods.dev/badge/commands/vieko/bonfire/end.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 | $0.00000 | $0.01125 |
| Opus 5.5 | $0.00000 | $0.00450 |
| Sonnet 5.5 | $0.00000 | $0.00225 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade A, and why
end 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 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.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End Session (fallback)
Outcome
<git-root>/.bonfire/index.md reflects the current session's work inside its two managed fence blocks — no native adapter required.
Acceptance Criteria
- Opt-in respected:
<git-root>/.bonfire/exists. If not, exit silently without creating anything. - Per-repo opt-out respected: if
<git-root>/.bonfire/config.jsonexists and has{ "auto": false }, exit silently. - File bootstrapped if missing: if
<git-root>/.bonfire/index.mddoesn't exist, create it from templates/index.md (which includes both fence markers). - In-flight fence updated between
<!-- bonfire:auto-inflight:start v1 -->and<!-- bonfire:auto-inflight:end -->:- First line inside the fence:
_Updated YYYY-MM-DD from <host>:<short-session-id> on \`_` - Then
## In flightheading - Then
### Goalwith a one-line session headline - If you have structured context (e.g., "what's done", "what's blocked"), add
### In Progress,### Blocked,### Next Stepssubsections - Otherwise add
### Modified fileswith output ofgit diff --name-only HEAD(up to 10 entries)
- First line inside the fence:
- Sessions fence updated between
<!-- bonfire:auto-sessions:start v1 -->and<!-- bonfire:auto-sessions:end -->:- One row per session, format:
- YYYY-MM-DD [<host>:<short-session-id>] <branch> — <one-line headline> - Insert the new row at the top (newest first)
- De-dupe by
[<host>:<short-session-id>]— same session updates its existing row instead of duplicating - Cap at 5 newest rows; drop the rest
- One row per session, format:
- Atomic write: write to a tmpfile and rename. Don't truncate-in-place.
Constraints
- Never modify content outside the fence markers. Everything outside is user-curated.
- Never inject fence markers into a file that doesn't have them. If
index.mdexists but lacks fences, exit without writing — user has chosen a different layout. - Short session id: use ≥8 random hex chars from the session's UUID (skip the first 8 chars if it's UUIDv7, since those encode the timestamp and collide for time-clustered sessions). If your agent has no native session id, derive a stable one from a conversation hash and document its scope.
- Host token: use a short identifier for your agent (
pi,claude,codex,opencode, etc.) so multi-agent users can tell rows apart. - Garbage detection: if the existing in-flight or sessions row matches
/no conversation (content|messages?)/i, treat it as missing (upstream bug pattern) and overwrite with current session data. - Stale detection: if the in-flight's
_Updated from <host>:<id>_line references a different session id than yours, overwrite with current session data. The in-flight should always reflect the most recent session.
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 · 66 lines · 0 tokens per session scan A 382692d72adb
end is a command published in the GitHub repository vieko/bonfire (10 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,125 tokens. 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.