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/travisjneuman/.claudeWrote 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/travisjneuman/.claude/update-counts)<a href="https://agentmods.dev/commands/travisjneuman/.claude/update-counts"><img src="https://agentmods.dev/badge/commands/travisjneuman/.claude/update-counts/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/travisjneuman/.claude/update-counts"><img src="https://agentmods.dev/badge/commands/travisjneuman/.claude/update-counts.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 | $0.00013 | $0.00450 |
| Opus 5.5 | $0.00005 | $0.00180 |
| Sonnet 5.5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
update-counts 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 14d 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
Refresh the existing public count pipeline only when publication is authorized:
bash ~/.claude/scripts/update-counts.sh --as-of=YYYY-MM-DD
The wrapper defaults to --write. An explicit --check is read-only; passing both modes is an error. Checking, testing, linting, building, or sample runs require separate owner authorization; they are not part of a source refresh.
The producer measures public real toolkit files and every manifest marketplace's committed HEAD blobs, not dirty/untracked plugin installations. It rejects incomplete/unreadable/misidentified clones, records selected revisions and clean/modified state, and writes one public snapshot with identity lists. Pins are snapshots, not a promise of latest upstream content.
It updates counts.json, the website's marketplace-counts.json, plugin.json, and specifically owned current numeric documentation (including skills/README.md). The website consumes these same snapshots locally and on hosted builds; it never recounts clones. Historical changelog counts remain historical.
It does not regenerate the index, stage/commit/push, render images, or update other repositories implicitly. If the discovery index needs refresh, explicitly run node ~/.claude/scripts/generate-index.mjs --write before the count write, because the index may update public settings.json.
Optional explicit consumers, measured in the same single pass:
node ~/.claude/scripts/generate-counts.mjs --write --as-of=YYYY-MM-DD \
--travis-repo /path/to/travisjneuman --portfolio-repo /path/to/tjn.portfolio
All destinations must preflight before any write. The profile requires claude-counts README markers and existing public Claude facts; the portfolio receives JSON only. Review the resulting diff and producer output. Do not rerun both consumer wrappers to remeasure the same inputs.
See Count pipeline for definitions, provenance, exact outputs, failure behavior, and the separate DESK-only media contract.
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.
- 14d ago Changed · +10 lines · -6 tokens per session 625ddd544095
- 25d ago Changed · +1 lines 8862de477f00
- 1mo ago First seen · 19 lines · 19 tokens per session scan A bc62777d02c5
update-counts is a command published in the GitHub repository travisjneuman/.claude (106 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 450 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.