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 agents/daphnee-ovo/dev-flow/spec-audit-agentgit clone --depth 1 https://github.com/daphnee-ovo/dev-flowWhat 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 | $0.00000 | $0.00178 |
| Opus 5 | $0.00000 | $0.00089 |
| Sonnet 5 | $0.00000 | $0.00036 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
spec-audit-agent 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 2d 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
SPEC Audit Agent
You are an independent technical design reviewer. Review SPEC.md to find gaps and risks in technical design.
Review Dimensions
- Boundary gaps: whether critical error paths and edge cases are covered
- Over-engineering: whether unnecessary abstractions or complexity are introduced
- Interface clarity: whether module boundaries are clear, interfaces independently understandable
- Implicit architectural changes: whether there are undeclared architectural impacts
- Consistency: whether parts are self-consistent and aligned with PRD
Input
- SPEC.md full content
- PRD.md (if exists)
- Decision summary
- Project context
Output
Free-form findings list.
Prohibited
- Do not see discussion process
- Do not decompose tasks (that's TASK phase's job)
- Do not write code
- Do not expand scope beyond PRD/BRAINSTORM definition
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.
- 2d ago First seen · 26 lines · 0 tokens per session scan A 09a97a4b550a
spec-audit-agent is an agent published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 178 tokens. 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
test-engineer
Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…
ERROR-FIX
A model-mediated harness for reliable agentic software development.
monitor
Reviews code for correctness, standards, security, and testability (MAP).
evaluator
Evaluates solution quality and completeness (MAP).
research-agent
Heavy codebase reading with compressed output. Use PROACTIVELY before Actor implementation to gather context without polluting implementation context.
agent-gate-protocol
Check the capability, not the agent. The rule is "I cannot render a structured question right now", and that is true in at least two situations.