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/resumegit 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 | $0.00007 | $0.00523 |
| Opus 5 | $0.00003 | $0.00262 |
| Sonnet 5 | $0.00001 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade C, and why
resume scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
position, not after — a phase read without the arc around it is a phase you cannot refuse work How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume the programme $1, or resolve it if $1 is empty.
Resolve the programme from the tree
git rev-parse --abbrev-ref HEAD
cat "<docsRoot>/programmes/INDEX.md"
Match the current branch against the branch column. $1 wins if given. Skip any row whose
status is closed — it is not a candidate, even if its branch matches. If nothing matches and
there is exactly one open programme, use it. If several exist and none matches, list them and
ask — do not guess, and do not fall back to "most recently modified", which is how a session ends
up writing into the wrong programme's ledger.
Read, in this order
<docsRoot>/programmes/<SLUG>/ledger.md— in full, starting with## The arc: the goal, the programme's terminal condition, and which phases are stillplanned. Read it before the position, not after — a phase read without the arc around it is a phase you cannot refuse work inside.<docsRoot>/programmes/<SLUG>/NEXT-SESSION.md— follow its "Start here" block verbatim
Read the prompt file itself rather than acting on any summary of it, including one in this conversation. That is deliberate: it stops the instructions being invoked in a stale copied form.
Run every check in the State table before acting
NEXT-SESSION.md's State table carries a verify with command beside every figure. Run all of
them and compare. In the repo this convention comes from, two documents currently disagree about
the same ahead-of-origin count, and one commit subject is literally "correct the ahead-of-origin
claim, which went stale as it was written."
Report any figure that has drifted, and correct NEXT-SESSION.md before continuing.
Then report, before doing any work
State: which programme you resolved and how; the arc — the goal, the programme's terminal
condition, the current phase, and every phase still planned; the position as the ledger
records it; what you measured and what drifted; and the phase's terminal condition you are working
toward, quoting its command and expected output. Then ask whether to proceed.
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 · 47 lines · 7 tokens per session scan C 77a199060101
resume is a command published in the GitHub repository longthread/claude-plugins (1 stars, last pushed 11d ago), licensed MIT. It adds 7 tokens to every session and 523 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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.