Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-pynpx agentmods add skills/terrene-foundation/kailash-coc-claude-py/sweepWrote 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/skills/terrene-foundation/kailash-coc-claude-py/sweep)<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/sweep"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/sweep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/sweep"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.03606 |
| Opus 5 | $0.00018 | $0.01803 |
| Sonnet 5 | $0.00007 | $0.00721 |
| Haiku 4.5 | $0.00004 | $0.00361 |
Grade A, and why
sweep 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 9d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sweep — Management Decision Report + Deferred-Quality Revisit (depth)
commands/sweep.md runs the outstanding-work sweeps; THIS skill carries the load-bearing
depth surfaces the command references: (1) the management decision report the sweeps
aggregate into, (2) the Sweep-N product-visibility revisit teeth for the deferred-quality
backlog, (3) § 5 Sweep 4 branch-enumeration discipline, and (4) § 6 Sweep 5's three
pre-condition modes (BUILD / repo-level-specs / orchestration-mode N/A) with the full gate
implementation + finding taxonomy. The finding CLASSIFIER (BUG / INVEST-NOW / INCREMENTAL, severity
decoupled, fail-closed) is OWNED by rules/product-completion-first.md — referenced here per
rules/specs-authority.md Rule 9, never restated.
1. The management decision report contract (the /sweep deliverable)
/sweep is the decision gate: a professional, high-quality management report FOR
DECISION-MAKING AT THAT JUNCTURE — invoked on demand, as the end-of-cycle gate before
/wrapup, and at product-visibility milestones (terminal wave converges / release tag). It
MUST produce, in this order:
- Completion status — which product milestones are complete AND visible (walking-skeleton
stands vs not); what fraction of the committed scope is done. Cite the durable receipt
(merged PR / journal DECISION / spec success-criterion) for each "complete" claim
(
rules/verify-resource-existence.mdMUST-4 — no self-attested completion). - ETA to completion — remaining BUG + INVEST-NOW work to a complete/visible product, in
autonomous cycles (sessions), NEVER human-days (
rules/autonomous-execution.md). State the basis (which open items, at what per-item cycle estimate). - Prioritized immediate queue — the open BUGs + INVEST-NOW issues, value-ranked
(
rules/value-prioritization.mdMUST-1, each anchored to a user-anchored source), each with its implication. - Deferred-quality backlog — the INCREMENTAL items, grouped by revisit trigger
(
after-milestone:<name>|on-demand), each with its value-anchor + why-deferred + the four generalized-1b conditions (blocking-safety note / value-anchor / acceptance criteria / revisit trigger). - Decision points — the INVEST-NOW-vs-defer JUDGMENT calls, each surfaced with
prioritization + implications + symmetric pros/cons + a recommended disposition
(
rules/recommendation-quality.mdMUST-1/2/3), for co-owner direction. The agent NEVER silently self-decides a judgment-bucket item (rules/product-completion-first.mdMUST-4). - Recommendation — the agent's recommended next steps, for ratification (never a bare menu;
rules/recommendation-quality.mdMUST-1).
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.
- 9d ago First seen · 206 lines · 36 tokens per session scan A 249d8ef7c612
sweep is a skill published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 24d ago), licensed Apache-2.0. It adds 36 tokens to every session and 3,606 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.