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/TheColliery/CoalTippleWrote 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/thecolliery/coaltipple/update)<a href="https://agentmods.dev/commands/thecolliery/coaltipple/update"><img src="https://agentmods.dev/badge/commands/thecolliery/coaltipple/update/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/thecolliery/coaltipple/update"><img src="https://agentmods.dev/badge/commands/thecolliery/coaltipple/update.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 | $0.00026 | $0.00644 |
| Opus 5.5 | $0.00010 | $0.00258 |
| Sonnet 5.5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
update 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 yesterday.
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.
This is a copy
88% identical to update — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
CoalTipple keeps itself current through the conductor (session start), gated by .coaltipple.json updateMode (ask | auto | remind | off, default ask) and throttled to once per updateCheckDays (default 14). Self-update runs only while routing is on: routing off (enableRouting: false, mode: "off" or disableRouting: ["all"]) silences the whole conductor, self-update included, and no stamp is written; with routing on, its own off-switch is updateMode: off. This command is the agent procedure each mode triggers — and a manual entry point. Always answer in the user's language; offer choices via your question tool; never spend tokens or change config without a chosen option.
ask — present the 3-way choice via your question tool:
- auto — the agent web-checks on a ~
updateCheckDayscadence and offers updates (~1-2K tokens/check). - remind — a free periodic reminder; the user runs the update themselves.
- off — no reminders.
Save the pick (no forced check — the chosen mode drives future sessions):
set updateMode (auto, remind or off) directly in the GLOBAL config file ~/.claude/.coaltipple.json (the one under CLAUDE_CONFIG_DIR if that is set) with your edit tool; an installed plugin has no scripts/. In a source checkout of CoalTipple, node scripts/configure.mjs --updateMode <auto|remind|off> does the same.
auto (the version CHECK — the only token spend, standing-consented):
- Get the latest published tag (graceful — never assume git/network is present):
git ls-remote --tags --sort=-v:refname https://github.com/TheColliery/CoalTipple.git | head -1(parse the trailingvX.Y.Z; ignore^{}deref lines). - Compare to the installed version in
.claude-plugin/plugin.json(the plugin cache copy, or the repo copy if working from source). - If a newer tag exists → OFFER (don't auto-run):
claude plugin update coaltipple@coaltipplethen/reload-plugins. If current → "up to date." - Graceful fallback (no-external-assumption): if
git ls-remotefails, git is missing, or there is no network, say "Can't check for updates offline — update manually withclaude plugin update coaltipple@coaltipplewhen you're back online" and stop. Never crash, never assume a version.
remind — nothing for the agent to do; the conductor already surfaced the free reminder line. (If invoked manually, run the auto check above on request.)
off — no update activity.
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.
- yesterday Changed f16b85f39496
- 1mo ago First seen · 26 lines · 26 tokens per session scan A 038ee7c1d6bb
update is a command published in the GitHub repository TheColliery/CoalTipple (6 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 644 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to update, differing in 16 lines, and is treated as a copy.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
crear-skill
Crear, probar y mejorar skills de forma iterativa. Usa cuando el usuario dice "crear skill", "crear habilidad", "build skill", "create a skill", "skill development", "desarrollar skill", "nueva habilidad". Usa el workflow: draft → test → review → improve → repeat con evaluación cuantitativa y qualitative review.