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 skills add timjensgrossinger/threnody --skill threnody-swarm-reviewgit clone --depth 1 https://github.com/timjensgrossinger/threnodyWrote 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/timjensgrossinger/threnody/threnody-swarm-review)<a href="https://agentmods.dev/skills/timjensgrossinger/threnody/threnody-swarm-review"><img src="https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-swarm-review/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/timjensgrossinger/threnody/threnody-swarm-review"><img src="https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-swarm-review.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 | $0.00099 | $0.01994 |
| Opus 5 | $0.00049 | $0.00997 |
| Sonnet 5 | $0.00020 | $0.00399 |
| Haiku 4.5 | $0.00010 | $0.00199 |
Grade A, and why
threnody-swarm-review 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 12d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threnody swarm review
Overview
This is the deep specialist review mode. It is intentionally more expensive
than threnody-fast-review; use it when the user asks for deep/security-critical
review, threat modeling, or a named dimension such as [dims=performance].
Complexity gating limits token blowout:
| Band | LOC | Dimensions run |
|---|---|---|
| trivial | < 50 | logic, edge |
| moderate | 50–200 | logic, edge, types |
| complex | > 200 | logic, edge, types, security, performance |
Security is always added when the file contains risk signals (SQL, exec, auth, tokens, etc.), but ordinary risk words do not automatically force high tier.
Tier → model is chosen per agent from raw file size × dimension reasoning-weight (no LLM call — pure heuristic, keeps fast-start):
| File/profile | edge / types (light) | logic / performance / security (reasoning-heavy) |
|---|---|---|
small < 230 |
low → cheap tier | low, or medium for dense/security-risk code |
mid 230–600 |
medium | medium, high only when dense |
large > 600 |
medium | high unless the file is flat/config-like |
| ordinary security risk | — | medium by default |
| concrete exploit primitive or explicit deep/critical request | — | high |
Synthesis is medium by default. It escalates to high only for explicit
deep/security-critical intent, concrete exploit primitives, or large finding
sets (for example ≥12 review agents). Never below medium; dedup/ranking is
reasoning-heavy.
Fast-start contract
Review swarm paths must return host_spawn_waves quickly: target under 5
seconds to handoff and under 30 seconds to first review-agent spawn. Cheap
review tiers are the default; high tier is reserved for explicit deep review,
security-critical wording, concrete exploit primitives, or large/dense files.
Do not block first spawn on optional refinement, consensus, learning aggregation, or deep planner calls. Run deterministic lint/context collection only when cheap, then start the first review wave.
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.
- 12d ago First seen · 227 lines · 99 tokens per session scan A d31c0596ad6c
threnody-swarm-review is a skill published in the GitHub repository timjensgrossinger/threnody (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,994 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
skillshare-codebase-audit
Cross-validate CLI flags, docs, tests, and targets for consistency across the codebase. Use this skill whenever the user asks to: audit the codebase, check for consistency issues, find undocumented flags, verify test coverage, validate targets.yaml, check handler split conventions, or verify oplog instrumentation.…
testing-anti-patterns
Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or…
structured-code-review
Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR…
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…
quality-gates
Expert knowledge in quality assurance gates, code quality standards, and automated checks. Use when enforcing quality standards.
am-agent-security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.