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.
npx agentmods add commands/longthread/claude-plugins/statusgit clone --depth 1 https://github.com/longthread/claude-pluginsWhat 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 | $0.00012 | $0.00982 |
| Opus 5 | $0.00006 | $0.00491 |
| Sonnet 5 | $0.00002 | $0.00196 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
status 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report on programme $1 (resolve as /programme:resume does). Pass --gates to also run the
slow gates.
This command writes nothing. Not the ledger, not NEXT-SESSION.md, not INDEX.md — even when
you find something wrong. That is the whole point: a status that quietly corrects the record cannot
be used to find out whether the record is honest, because running it makes the answer yes. Report
the drift and name the file to fix; /programme:handoff is what writes.
Use this when you want to know where things stand without starting work. /programme:resume reads
the same files and then begins.
1. Where the programme is
From <docsRoot>/programmes/<SLUG>/ledger.md and its NEXT-SESSION.md:
## The arcfirst — the goal, and the programme's terminal condition quoted verbatim. Say plainly that it is the programme's and that the one below is the phase's; a met phase condition read as a met programme condition is how a programme gets called finished with phases stillplanned.- what is done and what is left, from the arc's
statuscolumn: thedonerows, thecurrentone, and every row stillplanned. Do not invent a progress metric, and never read what has closed by counting Archive index rows — that table's own note says why. - the phase's terminal condition, quoting its
Command:andExpected output:verbatim
If the arc, the Current position and the Archive index disagree about what has closed, say so — that
is a real finding, not a formatting problem. An arc whose current row is not the phase
NEXT-SESSION.md describes is the same finding, and it is the one that means the programme has
drifted off its own map.
2. Whether the record is still true
NEXT-SESSION.md's State table carries a verify with command beside every figure. Run all of
them and put the claimed value beside the measured one. This is the section that earns the
command: every figure in these files was true when written, and the ahead-of-origin count in the
repo this convention comes from went stale so reliably that it is now recorded as a range.
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 First seen · 73 lines · 0 tokens per session scan A 8e0e5255a747
status is a command published in the GitHub repository longthread/claude-plugins (1 stars, last pushed 11d ago), licensed MIT. It adds 12 tokens to every session and 982 once invoked, about $0.0001 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
save
Save this conversation as a new or existing reusable context.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.
use
Connect a NeatContext context to this session.
export
Export a saved context as a bundle folder you can share.
mode
Choose how this session may switch contexts on its own.
extensions
Show what the connected context expects to reach, and whether this machine provides it.