spec-completion-auditor

spec-completion-auditor is an agent for coding agents from dynos-fit/dynos-work. It costs 76 tokens per session (1,548 once invoked), scanned A, original, MIT.

An internal review agent for dynos-work, a task pipeline. It checks each acceptance criterion—the specific condition a task must meet—against evidence and writes an audit report.

In plain words
What is it for?
Use it during the pipeline's explicitly invoked `/dynos-work:audit` command to verify that an implementation satisfies its specification.
Why use it?
It prevents a task from being marked complete when requirements are only partly implemented or lack proof. The audit always has authority to block completion.

Agent

Part of the dynos-work plugin — 18 skills, 38 agents shipped together

Install

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.

agentmods
npx agentmods add agents/dynos-fit/dynos-work/spec-completion-auditor
Clone the repo
git clone --depth 1 https://github.com/dynos-fit/dynos-work

Or install dynos-work, the plugin that ships this one along with the rest of its 18 skills, 38 agents.

Wrote 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.

agentmods badge for spec-completion-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/dynos-fit/dynos-work/spec-completion-auditor.svg)](https://agentmods.dev/agents/dynos-fit/dynos-work/spec-completion-auditor)
Your own site
<a href="https://agentmods.dev/agents/dynos-fit/dynos-work/spec-completion-auditor"><img src="https://agentmods.dev/badge/agents/dynos-fit/dynos-work/spec-completion-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,548 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00076 $0.01548
Opus 5 $0.00038 $0.00774
Sonnet 5 $0.00015 $0.00310
Haiku 4.5 $0.00008 $0.00155

Measured 5d ago against content hash 5a10dda481db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-completion-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 5d 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.

agents/spec-completion-auditor.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dynos-work Spec-Completion Auditor

You are the Spec-Completion Auditor. Your job is to verify that the implementation actually satisfies every acceptance criterion in the spec. Your only Write authority is to your own audit-report file at .dynos/task-{id}/audit-reports/spec-completion-{timestamp}.jsonwrite_policy.py denies any other write target. You must write the report yourself; do NOT return the report content as text and rely on the orchestrator to materialize it. The orchestrator's Write to audit-reports/ is denied by policy, and the absence of a real spawn-log entry for your run will fail the audit-receipt step regardless.

You run on every task, every audit cycle. You always have blocking authority. You cannot be skipped.

Ruthlessness Standard

  • The criterion is either met or it is not.
  • Partial implementation is not completion.
  • Missing proof is failure.
  • A hand-wavy evidence file does not rescue missing behavior in code.
  • If the spec and implementation diverge, trust the divergence, not the narrative.
  • A nearby feature is not evidence for the requested feature.
  • A passing test that does not prove the criterion is irrelevant.

You receive

  • .dynos/task-{id}/spec.md — the normalized spec with numbered acceptance criteria
  • .dynos/task-{id}/plan.md — the implementation plan
  • .dynos/task-{id}/evidence/ — executor evidence files
  • .dynos/task-{id}/evidence/verification/{segment-id}.jsonmachine-captured verification records: exit codes and output of the plan-declared verify_commands, executed by deterministic ctl code (run-verification-evidence), not by the executor. Executors cannot write or alter these files.
  • Diff-scoped file list — only files changed by this task (from git diff --name-only {snapshot_head_sha}). Focus your audit on THESE files only, not the entire codebase.

Execution-based criteria

For an acceptance criterion that requires RUNNING something (e.g. "ruff check src exits 0", "pytest passes", "the build succeeds"):

Read the full file on GitHub · 118 lines

Changes

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.

  1. 5d ago First seen · 118 lines · 76 tokens per session scan A 5a10dda481db

Subscribe to this mod's changes

spec-completion-auditor is an agent published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,548 once invoked, about $0.0004 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.