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 kitchen-engineer42/joharnessburg/plugin install johnWrote 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/kitchen-engineer42/joharnessburg/endurance)<a href="https://agentmods.dev/commands/kitchen-engineer42/joharnessburg/endurance"><img src="https://agentmods.dev/badge/commands/kitchen-engineer42/joharnessburg/endurance.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 | $0.00092 | $0.00635 |
| Opus 5 | $0.00046 | $0.00318 |
| Sonnet 5 | $0.00018 | $0.00127 |
| Haiku 4.5 | $0.00009 | $0.00064 |
Grade A, and why
endurance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
When this command fires:
-
Parse the user's argument. Everything after
/john:endurance(joined into one string) is the endurance goal — a short, concrete statement of what the long run is trying to produce. The--clearflag (if present, alone) clears the active endurance goal. -
Invoke the script via Bash:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/set_endurance.py" <user-args>Pass the goal text as a single argument (quote it). For
--clear, pass only--clear. -
The script returns JSON with
action: "set" | "clear" | "show". Show the user:- For
set: confirm the goal is now written to<cwd>/.john/workspace.jsonundersession_metadata.endurance_goal. Tell them the SessionStart hook will inject it into the system prompt at the top of every session in this directory from now on — so the goal survives context compaction and fresh-terminal restarts. - For
clear: confirm the goal is removed. SessionStart will fall back to the "no endurance goal set" message. - For
show(no args and no--clear): print the currently-set goal, or note that none is set.
- For
-
After a successful
set, gently remind the user that this is best used for real long runs — not every John session needs an endurance goal. A short Q&A session or a one-phase iteration is fine with just the project intent at the top of PLAN.md. Endurance mode is for runs that span hours, multiple compactions, or many ralph-loop iterations. -
On
success: falsewith "No .john/workspace.json found", tell the user to run/john:initfirst — endurance goals attach to a John workspace.
Endurance mode pairs with the ralph-loop and context-management skills — the goal is what survives compaction and what you re-align to after each iteration.
One behavioral consequence (see vertical-workflows): with an endurance goal set, John assumes the session is workflow-configured (/effort ultracode, dynamic workflows available) and will not pause a long run to ask the user to confirm config. If the Workflow tool is genuinely absent, John falls back to inline dispatch and notes it in PLAN.md rather than stopping. Users starting an endurance run should set up the session per the README's "Running John with dynamic workflows" recipe first.
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 · 30 lines · 92 tokens per session scan A 17ba6e15c485
endurance is a command published in the GitHub repository kitchen-engineer42/joharnessburg (9 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 635 once invoked, about $0.0005 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
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
ccc-orchestrate
Sequential and tmux/worktree orchestration guidance for multi-agent workflows.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
save
Save the current session digest. Fans out across every writable memory tier per the house-map. Tier 0 always; Tier 1 if reachable; Tier 2 only if registered writable with auth. Each tier independent — failures degrade gracefully.
design
A command that turns an existing plan into a detailed technical design for building the feature.