Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tbobm/dont-burn-it-all/plugin install dont-burn-it-allWrote 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/tbobm/dont-burn-it-all/burn)<a href="https://agentmods.dev/commands/tbobm/dont-burn-it-all/burn"><img src="https://agentmods.dev/badge/commands/tbobm/dont-burn-it-all/burn/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/tbobm/dont-burn-it-all/burn"><img src="https://agentmods.dev/badge/commands/tbobm/dont-burn-it-all/burn.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 | $0.00032 | $0.00357 |
| Opus 5 | $0.00016 | $0.00179 |
| Sonnet 5 | $0.00006 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
burn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the burn CLI once for the user and report its output. Do NOT loop or re-invoke it — each
/burn is a single, self-contained launch. The human decides when to run it again.
Steps:
- Build the binary if it is missing:
test -x "${CLAUDE_PLUGIN_ROOT}/burn" || go build -o "${CLAUDE_PLUGIN_ROOT}/burn" "${CLAUDE_PLUGIN_ROOT}" - Run it, passing the user's arguments verbatim:
"${CLAUDE_PLUGIN_ROOT}/burn" $ARGUMENTS - Surface the summary: current 5-hour usage %, headroom to target, sessions run, any errors.
Notes:
- Launch mode needs
--goal "<task>"(e.g./burn --goal "write unit tests for pkg/foo" --jobs 4). - Sessions prompt for permissions by default; add
--dangerously-skip-permissionsto run unattended. --watchpolls usage and notifies at the target, spawning nothing.- The first launch runs a ~3-minute preflight that proves sessions bill to the subscription (not pay-per-token API); this is intentional and cannot be skipped. If it reports a token or billing-env problem, relay the fix and stop — do not try to work around it.
- If a permission prompt blocks reading the OAuth credential, tell the user to run the command
themselves with
! "${CLAUDE_PLUGIN_ROOT}/burn" $ARGUMENTS.
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.
- 8d ago First seen · 25 lines · 32 tokens per session scan A bc21b58c76f7
burn is a command published in the GitHub repository tbobm/dont-burn-it-all (8 stars, last pushed 7d ago), licensed MIT. It adds 32 tokens to every session and 357 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
atomic-plan
Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.
challenge-swarm
Multi-lens design challenger. Reads a design/spec/plan/proposal, profiles it (who can reach it, whose data, what being wrong costs), then seats 3-6 expert lenses from a 30-lens catalog spanning engineering, data/ML, business, finance, communication, and delivery — each seated only with a cited stake, reflexive picks…
subagent-implementation
Orchestrate implement→review subagent loop until task complete. Reads the approved spec, writes a thin brief to .claude/.scratchpad/, dispatches fresh-context subagents, loops until reviewer signs off, commits per green iteration, then updates repo docs.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
documentation
Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).