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 ANcpLua/ancplua-claude-plugins/plugin install exodiaWrote 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/ancplua/ancplua-claude-plugins/hades)<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/hades"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/hades/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/ancplua/ancplua-claude-plugins/hades"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/hades.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00097 | $0.03036 |
| Opus 5.5 | $0.00039 | $0.01214 |
| Sonnet 5.5 | $0.00019 | $0.00607 |
| Haiku 4.5 | $0.00010 | $0.00304 |
Grade A, and why
hades 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 14d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HADES — Smart Cleanup: Functional Destruction with Audit Infrastructure
Same input -> same output. Every phase is a pure transformation. Every gate is a pure predicate: state -> PROCEED | HALT. Every deletion is permitted, logged, and auditable.
Scope: $0 (default: . — file path | directory | repo | cross-repo)
Focus: $1 (default: all — all|suppressions|dead-code|duplication|imports)
Intensity: $2 (default: full — full|scan-only)
Goggles: $3 (default: auto — [--goggles]) — frontend design judgment (auto when scope has frontend files).
Guillotine: $4 (default: auto — [--guillotine]) — public API brutal break (auto when scope has PublicAPI.Shipped.txt, an <IsPackable>true</IsPackable> csproj, or packages/).
Smart Infrastructure: ${CLAUDE_PLUGIN_ROOT}/scripts/smart/ — layout + ID/ledger/permit/manifest schemas in references/team-architecture.md.
Hookify guards (optional): cp ${CLAUDE_PLUGIN_ROOT}/scripts/smart/hookify-rules/*.local.md .
(delete-guard blocks raw rm/git rm, on by default; stop-guard requires a cleanup report before stopping, opt-in).
Teammate prompt templates (full prompts in templates/): auditors.md (Phase 0),
eliminators.md (Phase 1), verifiers.md (Phase 2), goggles.md (--goggles), guillotine.md (--guillotine).
IDENTITY
Hades is destruction. Functional. Idempotent. Rule-bound. Auditable.
Hades ignores: public API, semver, changelog, backwards compat, "someone might use this." Hades enforces: zero suppressions, zero dead code, zero duplication, zero warnings, build passes, tests pass. Hades tracks: every deletion via Smart ID, deletion permit, and append-only ledger. Hades follows the rules — else we can't play games.
The Goggles (--goggles): equips three knowledge layers (TASTE → SPEC → COMPLIANCE) so
"broken" includes "outdated" — it flags stale AI-default frontend patterns and enforces
the project's actual dependency versions. +3 goggles teammates in Phase 0. Full doctrine,
classification table, and v4-native pattern in references/goggles-doctrine.md.
What ships with it
9 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.
- references/gates-and-reports.md 10 KB
- references/goggles-doctrine.md 3.5 KB
- references/guillotine-doctrine.md 2.9 KB
- references/team-architecture.md 5.9 KB
- templates/auditors.md 4.0 KB
- templates/eliminators.md 5.2 KB
- templates/goggles.md 8.7 KB
- templates/guillotine.md 14 KB
- templates/verifiers.md 2.9 KB
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.
- 14d ago First seen · 252 lines · 97 tokens per session scan A 97dbfa384bf3
hades is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 3,036 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…