Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add longthread/claude-plugins/plugin install programmeWrote 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/init)<a href="https://agentmods.dev/commands/longthread/claude-plugins/init"><img src="https://agentmods.dev/badge/commands/longthread/claude-plugins/init.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.01704 |
| Opus 5 | $0.00010 | $0.00852 |
| Sonnet 5 | $0.00004 | $0.00341 |
| Haiku 4.5 | $0.00002 | $0.00170 |
Grade A, and why
init 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap a programme called $1 so that multi-session work on it survives session boundaries.
If $1 is empty, ask for a name before doing anything else. Derive <SLUG> from it: lowercase,
non-alphanumerics to hyphens.
1. Establish the ground truth
Run these and use the results; do not accept any figure from the conversation:
git rev-parse --show-toplevel
git rev-parse --abbrev-ref HEAD
git remote -v
date +%Y-%m-%d
Read .claude/session-continuity.json if it exists for docsRoot (default docs) and
compareBranch (default origin/main, or origin/master if that is what the remote has).
2. Refuse when it does not fit
A ledger suits work with a running thread across sessions. For a repo that is a series of unrelated tickets it goes stale and then actively misleads — worse than nothing.
If <docsRoot>/programmes/<SLUG>/ already exists, stop and say so. Do not overwrite a ledger;
offer /programme:resume <SLUG> instead.
Before creating anything else, if nothing in the conversation or the repo already shows a running
multi-session thread, ask the user directly: is $1 ongoing work a later session would need to
resume, or a series of unrelated tickets? The test is whether a session would ever have to ask
"where were we?" — if not, a ledger only rots. Do not proceed on silence; the user can override and
say to bootstrap anyway.
3. Create the files
Copy from ${CLAUDE_PLUGIN_ROOT}/templates/, substituting <PROGRAMME_NAME>, <SLUG>, <DATE>,
<BRANCH>, <COMPARE_BRANCH>, <DOCS_ROOT>. Substitute only those six literal token strings —
every other angle-bracketed span in a template is content, not a placeholder for you to fill:
ledger.md's archive/<YYYY-MM-DD>-<phase>.md and NEXT-SESSION.md's <the spec or plan this phase executes> are filled in later, by whoever writes those entries. ## The arc's three spans
and NEXT-SESSION.md's <a command a later session can actually run> /
<what it prints once this phase is done> are filled by step 5's interview, not by this copy.
A blanket replace of every <…> corrupts all eight. Copy each template's header
verbatim — those headers are the mechanism, and every rule in them is stated in exactly one place.
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.
- 6d ago First seen · 117 lines · 20 tokens per session scan A bd28a0c9ec6f
init is a command published in the GitHub repository longthread/claude-plugins (1 stars, last pushed 17d ago), licensed MIT. It adds 20 tokens to every session and 1,704 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
docs
Docs-only change for a ready-for-agent ticket. No application code.
lead
Tech lead: classify, quiz, ticket on the owning repo, dispatch. Do not implement.
poc
Start a hypothesis-driven POC with hard timebox. Skips 80% of the production pipeline; forces ship/pivot/kill decision at expiry.
rfc
RFC process for cross-team decisions. Create, track, and close RFCs. Accepted RFCs auto-create ADRs.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
migrate
Migrate existing PROJECT.md to the latest greatcto schema — appends missing fields without touching existing values.