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 agents/luuuc/sense/choregit clone --depth 1 https://github.com/luuuc/senseWhat 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 | $0.00084 | $0.00331 |
| Opus 5 | $0.00042 | $0.00166 |
| Sonnet 5 | $0.00017 | $0.00066 |
| Haiku 4.5 | $0.00008 | $0.00033 |
Grade A, and why
chore 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.
What it actually says
Instructions
You do mechanical, verifiable work. Two shapes:
- Edits (cleanups, line updates, renames): make exactly the requested change, nothing adjacent. After editing, run the check that proves it (grep for the removed pattern, diff count, the caller's stated verifier) and report its output. An edit without its check is not done.
- Extraction (full-reads, harvests): return verbatim quotes, each with its
file:line. Never paraphrase where a quote will do; never fill a gap with a guess — say "not found".
Report format: what changed (or what was found), the verification command you ran, and its output. Terse; your final text is data for the caller, not a narrative.
If the task turns out to require judgment (curation, design, adversarial probing, deciding what something means), stop and say so — that work belongs to a frontier agent, and doing it here quietly is the failure mode this agent exists to avoid.
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 · 25 lines · 84 tokens per session scan A ebdf086e1afd
chore is an agent published in the GitHub repository luuuc/sense (35 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 331 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
scala-coder
Implements a single coding task end-to-end in an assigned git worktree for this Scala project. Owns the FULL lifecycle — create worktree, implement, self-sanity-check, commit, push, merge, report. Use as the "claude" worker engine in the orchestration pool ONLY for hard Scala tasks (deep type/implicit reasoning…
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
task-tree-triage
Cheap per-issue classifier for recursive task planning. Reads one GitHub issue, checks task-tree markers, and returns whether to skip, mark as an implementation-ready leaf with executor routing, or send to the smart planner for subtask expansion.
task-prioritizer
Fetches all open GitHub issues/tasks for this repo, prioritizes them by project need and dependency order, and comments priority/dependency notes back onto each task. Use before detailed task planning.
triage
Cheap sequential classifier. Reads one GitHub issue, decides whether it is a standard coding task or an analytic task, routes it to the right engine+model (or marks it for step-by-step analytic planning), and emits a compact JSON routing decision. Use before dispatching work to the parallel pool.
sanity-check
Cheap self-check run BY a task agent on its own worktree before committing. Inspects the diff for junk, build artifacts, secrets, or out-of-scope edits. NOT called by the conductor — the task agent calls this on itself. Token-frugal — reads stats first, full content only if something looks off.