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/longthread/claude-pluginsWrote 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/longthread/claude-plugins/mode)<a href="https://agentmods.dev/commands/longthread/claude-plugins/mode"><img src="https://agentmods.dev/badge/commands/longthread/claude-plugins/mode/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/longthread/claude-plugins/mode"><img src="https://agentmods.dev/badge/commands/longthread/claude-plugins/mode.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 | $0.00009 | $0.00499 |
| Opus 5.5 | $0.00004 | $0.00200 |
| Sonnet 5.5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
mode 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 7d 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
Set programme $1's mode to $2 (resolve as /programme:resume does). $2 must be exactly
assisted, supervised or autonomous; anything else is refused.
What a mode does at each point of a relay is stated where that point happens — /programme:handoff
for the interview and the relay, /programme:resume for whether to proceed. This command only
records the choice, after checking it can be honoured.
1. Check the dependencies — supervised and autonomous only
Supervised and autonomous relay through herdr, using the herdr skill. The herdr dependency check passes only if all three hold:
command -v herdrsucceeds;herdr statusreaches a running server — a client/server version difference that herdr itself reports as compatible passes;- the
herdrskill is in this session's own list of available skills. A skill file on disk that this session cannot load does not count.
If any check fails, refuse: name the check and its fix — install herdr, start its server, install
or enable the herdr skill — and change nothing. assisted never runs this check; it needs nothing
but this plugin.
2. Write the one cell
In <docsRoot>/programmes/INDEX.md, set the programme's mode cell to $2. If the table has no
mode column yet, add it as the last column — header, separator, and a blank cell on every other
row — then write the cell. Change nothing else, and do not commit: the edit lands with the next
commit, like any INDEX.md change.
3. Report
Old mode — the cell read as INDEX.md's header comment states, quoting the raw cell when it was
blank or not one of the three — → new mode; each check's result when one ran; and the branch whose
INDEX.md you edited. INDEX.md is per branch, so a session in another branch's worktree keeps
that branch's mode until this change is merged there.
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.
- 7d ago First seen · 41 lines · 9 tokens per session scan A 6416d36f575a
mode is a command published in the GitHub repository longthread/claude-plugins (1 stars, last pushed 9d ago), licensed MIT. It adds 9 tokens to every session and 499 once invoked, about $0.0000 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 2026-10-08.
Other commands, from other repositories
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
feature
Implement a ready-for-agent feature ticket in this checkout. Do not expand the ask.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
review
Harsh maintainability review of one PR. Comments, not patches. Do not merge.
telemetry
Pull breakage or product-performance evidence. Funnels, feature completion, errors. Do not implement.
ci
Watch gh pr checks until green and fix failures on this branch. Do not merge.