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/audit-progressive-disclosurenpx skills add melodic-software/claude-code-plugins --skill audit-progressive-disclosuregit 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/audit-progressive-disclosure)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-progressive-disclosure"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-progressive-disclosure.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 | $0.00259 | $0.03218 |
| Opus 5 | $0.00130 | $0.01609 |
| Sonnet 5 | $0.00052 | $0.00644 |
| Haiku 4.5 | $0.00026 | $0.00322 |
Grade A, and why
audit-progressive-disclosure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Current branch: !git branch --show-current 2>/dev/null || echo "unknown"
Uncommitted .md files (sample, first 10; empty = none matched or the probe returned nothing): !git status --porcelain >/dev/null 2>&1 && { git status --porcelain 2>/dev/null | grep -E '\.md"?$' | head -10; :; } || echo "(git status unavailable)"
Purpose
Agent-facing instruction markdown, CLAUDE.md/AGENTS.md, .claude/rules/, skill/agent/command
bodies, their bundled spokes, has a load cost set by its tier: always-loaded content is paid
every session, invocation-loaded content recurs for the rest of the session once triggered, and
on-demand content is free until read. This skill audits both directions of that economy: content
that should move DOWN a tier (split opportunities), and existing hub/spoke structures whose
pointers no longer let an agent pull exactly the file it needs (structure defects). It is a
read-only classifier: findings carry treatment guidance; the author applies every edit.
Full tier tables, official numbers, split triggers, and pointer-quality criteria: read context/tier-model.md when adjudicating any finding that needs the exact threshold, routing rule, or citation posture (Anthropic-prescribed vs corroborated vs community).
Finding shapes and treatments
| Lane | Shape | What it looks like | Default tier | Treatment |
|---|---|---|---|---|
| split | oversize |
File at/approaching its tier's size guidance (SKILL.md approaching 500 lines; CLAUDE.md above ~200; references per the TOC bands). Ceilings, not targets. Size alone below the cap is no finding | 2 | Add a hierarchy layer: name the sections to push into spokes, each behind a conditioned pointer |
| split | mixed-concerns |
Mutually-exclusive contexts co-resident (content that never co-executes), category straddle, multi-topic rules file, cross-file contradiction | 2 | Split by concern. One topic per file; name the proposed split seams |
| split | tier-mismatch |
Content at the wrong tier: a procedure grown inside CLAUDE.md (→ skill), path-local rules in a global file (→ scoped rule), reference detail inline in a hub (→ spoke), always-loaded content not needed every session (→ demote behind a pointer) | 1 when an official routing rule decides it; else 2 | Route down-tier per the rule; the finding names source section and destination surface |
| structure | blind-pointer |
Pointer with no when-to-read clause, unmarked execute-vs-read intent, or a vague target name (doc2.md, utils) |
2 | Attach the condition and intent; rename the target descriptively. On skill descriptions, a missing when-NOT-to-use clause is advisory color (community-sourced), never a violation |
| structure | orphan-spoke |
Bundled spoke no hub references. Unreachable by pointer | 2 | 3-way: add the missing pointer, merge the content up, or delete the spoke |
| structure | deep-nesting |
Spoke-to-spoke chain, required reading more than one level from the hub (documented partial-read failure) | 2; 1 when the chain is the only path to required content | Re-link the deep target directly from the hub, or flatten |
| structure | missing-toc |
Reference file >300 lines with no TOC = definite; 100–300 lines with none = awareness only, citing the official 100-vs-300 conflict | 1 (>300) / 3 (100–300) | Add a TOC at top (or a grep recipe for lookup-shaped content) |
What ships with it
11 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.
- context/tier-model.md 9.3 KB
- evals/evals.json 7.1 KB
- evals/fixtures/broken-skill/context/details.md 93 B
- evals/fixtures/broken-skill/context/queries.md 90 B
- evals/fixtures/broken-skill/context/scratch-notes.md 99 B
- evals/fixtures/broken-skill/SKILL.md 218 B
- evals/fixtures/healthy-skill/reference/redlining-rules.md 274 B
- evals/fixtures/healthy-skill/SKILL.md 562 B
- evals/fixtures/mixed-instructions.md 1.5 KB
- scripts/detect.sh 12 KB runs code
- scripts/detect.test.sh 10.0 KB runs code
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 · 161 lines · 259 tokens per session scan A 695b2192b843
audit-progressive-disclosure is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 259 tokens to every session and 3,218 once invoked, about $0.0013 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.
generate-tree-structure
For tree/maze generation: spanning trees, random mazes, graph coverage. Uses frontier-based exploration with configurable traversal order.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.