status

A command for starting a programme that continues across multiple coding sessions. It creates a ledger, a handoff prompt, a deferred-work file, and a pointer from the project instructions.

In plain words
What is it for?
Use it to bootstrap ongoing work after checking the repository, branch, remote, date, and session-continuity settings.
Why use it?
It preserves the goal, decisions, and next steps between sessions, while refusing to overwrite an existing programme or start one when the work is only a collection of unrelated tasks.

Command

Install

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.

agentmods
npx agentmods add commands/longthread/claude-plugins/status
Clone the repo
git clone --depth 1 https://github.com/longthread/claude-plugins
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 982 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash 8e0e5255a747, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/programme/commands/status.md · 73 lines

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 arc first — 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 still planned.
  • what is done and what is left, from the arc's status column: the done rows, the current one, and every row still planned. 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: and Expected 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.

Read the full file on GitHub · 73 lines

Changes

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.

  1. yesterday First seen · 73 lines · 0 tokens per session scan A 8e0e5255a747

Subscribe to this mod's changes

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.