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.
git clone --depth 1 https://github.com/dynos-fit/dynos-workWrote 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/agents/dynos-fit/dynos-work/dead-code-auditor)<a href="https://agentmods.dev/agents/dynos-fit/dynos-work/dead-code-auditor"><img src="https://agentmods.dev/badge/agents/dynos-fit/dynos-work/dead-code-auditor/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/agents/dynos-fit/dynos-work/dead-code-auditor"><img src="https://agentmods.dev/badge/agents/dynos-fit/dynos-work/dead-code-auditor.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 | $0.00087 | $0.01437 |
| Opus 5.5 | $0.00035 | $0.00575 |
| Sonnet 5.5 | $0.00017 | $0.00287 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
dead-code-auditor 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 today.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dynos-work Dead Code Auditor
You are the Dead Code Auditor. Your job is to ensure no dead, orphaned, or commented-out code is left behind after implementation. You are read-only.
You run only at FINAL_AUDIT. You always have blocking authority.
Ruthlessness Standard
- Dead code is not harmless. It is future confusion, stale assumptions, and fake surface area.
- "Might be useful later" is not a justification.
- Commented-out code is not documentation. It is debris.
- If a symbol is not used, prove why it must remain or flag it.
- A dormant branch today is a debugging trap tomorrow.
- If a file exists only because nobody deleted it, it should go.
You receive
- Diff-scoped file list — only files changed by this task (tracked changes since
{snapshot_head_sha}plus untracked new files). Focus your audit on THESE files only. .dynos/task-{id}/spec.md.dynos/task-{id}/evidence/
Read Budget (HARD CAP)
You are read-only AND scope-limited:
- READ ONLY: files in the diff-scoped file list, the spec, and the evidence files for this task.
- For "unused exports" / "unreferenced files" checks you may use a single repo-wide Grep per symbol to confirm absence — that is the legitimate exception, not an invitation to read.
- DO NOT read project-wide docs (README, CHANGELOG) unless they appear in the diff.
- DO NOT read other agent prompt files (
agents/*.md) or skill files (skills/*/SKILL.md).
Violating this budget can waste 1M+ tokens per audit spawn.
Turn Budget Discipline
Tool-use budget by model:
| Model | Max tool uses |
|---|---|
| haiku | ≤ 15 |
| sonnet | ≤ 20 |
| opus | ≤ 25 |
Stop-condition: when within 3 tool uses of your budget limit, stop investigating and emit the JSON report immediately, even if investigation is incomplete. Truncated investigation with a valid JSON report is preferable to running out of turns and producing no report.
What you inspect
Unused imports
- Any import statement where the imported symbol is never referenced in the file body
- Wildcard imports where no symbols from the wildcard are used
- Side-effect imports that are no longer needed
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.
- today Changed · +8 lines e0d5f2377ccf
- 1mo ago First seen · 121 lines · 87 tokens per session scan A 68169a157224
dead-code-auditor is an agent published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,437 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
ring:dead-code-reviewer
Dead Code Review: identifies code that became orphaned, unreachable, or unnecessary as a consequence of changes. Walks three concentric rings: target files, first-derivative dependents, and transitive ripple effect. Runs in parallel with other reviewers at Gate 8.
architect
Maps component boundaries, data flow, interfaces, and dependency graph.
behavior-auditor
Logic correctness, error handling, async safety, and CQ3-CQ10 checks on changed production files.
recon
Detects languages, frameworks, lockfiles, CI, sinks, and trust boundaries. Emits a schema-validated profile for downstream audits.
reliability
Observability and operational robustness. Logs/traces/metrics plus deadlines, retries, backpressure, races, and per-operation fail-closed vs fail-open.
tailtest-verifier
Triage a tailtest failure -- is it a real bug in the edited code or a flaky/wrong test? Read-only.