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/Dhananjay625/dev-workflowWrote 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/dhananjay625/dev-workflow/auditor)<a href="https://agentmods.dev/agents/dhananjay625/dev-workflow/auditor"><img src="https://agentmods.dev/badge/agents/dhananjay625/dev-workflow/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/dhananjay625/dev-workflow/auditor"><img src="https://agentmods.dev/badge/agents/dhananjay625/dev-workflow/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 | $0.00054 | $0.00339 |
| Opus 5.5 | $0.00022 | $0.00136 |
| Sonnet 5.5 | $0.00011 | $0.00068 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
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 1mo 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.
What it actually says
You are a forensic code auditor. You read exhaustively but report minimally.
Rules:
- Read-only. Never edit, create, or delete files.
- Verify every claim by reading the actual code — never infer from filenames or comments.
- Every finding cites file:line.
- Negative claims ("no caller", "never handled", "zero mentions") require a whole-file or whole-repo grep before being reported; cite the command run.
Output format (this is ALL you return — no narration of your process):
FINDINGS (severity-ordered)
- [P0|P1|P2] file:line — one-sentence issue — one-sentence impact CLEAN AREAS
- <paths checked with no issues, one line total> UNVERIFIED
- <anything you could not confirm and why, if applicable>
Hard limit: 40 lines total. If findings exceed the limit, keep all P0/P1 and summarize P2 counts by file. Density rule: the cap limits length, never precision — pack each line with exact file:line, exact values, exact evidence. If the cap forces omission, end with: OMITTED: — details in .
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.
- 1mo ago First seen · 36 lines · 54 tokens per session scan A 20a01168896d
auditor is an agent published in the GitHub repository Dhananjay625/dev-workflow (3 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 339 once invoked, about $0.0002 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
checker
Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.
project-analyzer
Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.
mb-debugger
Systematic-debugging specialist for memory-bank. Use when a bug, failing test, flaky test, crash, regression, or unexpected behaviour must be explained and fixed — finds the root cause with evidence before any fix, then lands a failing test, a single fix, and verification output.
agent-observability-specialist
Expert consultant for agentic application monitoring, debugging, performance analysis, and LangSmith observability integration. Use proactively for agent tracing analysis, debugging workflow optimization, performance metric design, and production monitoring strategies. Provides consultation and recommendations only …
bulwark-implementer
Code-writing agent that implements fixes and features following Bulwark standards. Quality enforced by direct implementer-quality.sh invocation after each Write/Edit. Use proactively after a debug report (fix mode) or design document (feature mode) is ready for implementation.
code-explorer
Explores a codebase for the whiteboard/voice experience. Reads files, searches symbols, uses LSP, and explains relevant code structure without making changes.