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 skills/melodic-software/claude-code-plugins/sweep-allnpx skills add melodic-software/claude-code-plugins --skill sweep-allgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/sweep-all)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/sweep-all"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/sweep-all.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 | $0.00170 | $0.02702 |
| Opus 5 | $0.00085 | $0.01351 |
| Sonnet 5 | $0.00034 | $0.00540 |
| Haiku 4.5 | $0.00017 | $0.00270 |
Grade A, and why
sweep-all 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sweep all disciplines
A declared second species in this plugin: NOT a corrector. Every sibling
skill re-anchors ONE discipline; this one carries no discipline of its own. It is a pure router that COMPOSES the correctors into a single batched
re-anchor pass. It holds zero discipline text: the disciplines live in the
correctors, the shared method lives in
${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md,
and membership + order live in each corrector's own tier metadata. This skill
names no members. It globs and reads them, so the bundle cannot drift from a
hand-maintained list.
Two modes
- Session-start digest (cheap, default when nothing has happened yet). Derive the posture from the skill listing and each corrector's tier metadata. NO corrector bodies load, NO audit runs. Report which correctors are core (run every session), which are situational (relevance-gated), and which are never-batched. This is the conversation-start case: set posture, audit nothing.
- Full batch pass (mid-session, or on explicit request). Preflight that the fan-out can inherit this conversation (mandatory. See Preflight), then fan out an audit-only subagent per in-scope corrector and apply their corrections once, on the main thread, in a fixed order (below). A failed preflight degrades to mode 1 with the exact degrade token as the report's first line (see Preflight).
Resolving membership (never named inline)
Glob the sibling corrector directories and read each one's
metadata.discipline-batch (core / situational / never) and
metadata.discipline-batch-rank. The runbook never hardcodes member names;
the tier is colocated with each corrector, so changing a shipped tier is a PR
to that corrector. Drift is structurally impossible.
- core. In scope every session.
- situational. In scope only when relevant to THIS conversation. Route from the corrector's own listing description (its trigger phrases and "at conversation start on …" clause), not from a guess. Report which situational correctors were included and which were skipped and why. A skip is always reported, never silent.
- never. Excluded from the batch by execution or interaction class
(heavier fan-out tiers; correctors that need a non-fork fresh context or
stop to remediate with the user). Membership is whichever correctors
declare
discipline-batch: never. This runbook does not enumerate them. Report that they exist (from the glob) and are invoked directly, not batched.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 187 lines · 170 tokens per session scan A 6aa9261d3a67
sweep-all is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 170 tokens to every session and 2,702 once invoked, about $0.0009 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
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
propagate-then-search
For constraint problems: eliminate impossibilities before guessing, reduce search space through inference, fail fast on contradictions.
stack-based-backtrack
For search with undo: explicit decision stack, backtracking when paths fail, depth-first exploration with state restoration.
build-priority-queue
For ordered processing: A search, Dijkstra, event simulation, task scheduling. Efficient min/max extraction with heap-based queue.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.