dsd-phase-auditor

dsd-phase-auditor is a skill for Claude Code, Codex from frozenpepper/deepseek-and-destroy. It costs 18 tokens per session (176 once invoked), scanned A, original, MIT.

A read-only review of one frozen phase of a software project against its agreed requirements and evidence. A frozen phase is a completed project stage whose state should not change during the review.

In plain words
What is it for?
Auditing cross-task connections, checking that plans match the resulting code, finding stale evidence, and assessing whether finalization would create a circular dependency.
Why use it?
A phase can appear finished while tasks, integration, tests, or final records are incomplete or contradictory. This finds missing proof and defects so the person in charge can decide whether the phase is ready.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Auditing cross-task connections, checking that plans match the resulting code, finding stale evidence, and assessing whether finalization would create a circular dependency.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/frozenpepper/deepseek-and-destroy/dsd-phase-auditor
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.

Any agent
npx skills add frozenpepper/deepseek-and-destroy --skill dsd-phase-auditor
Clone the repo
git clone --depth 1 https://github.com/frozenpepper/deepseek-and-destroy

Made for: Claude Code, Codex.

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 dsd-phase-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/frozenpepper/deepseek-and-destroy/dsd-phase-auditor/github.svg)](https://agentmods.dev/skills/frozenpepper/deepseek-and-destroy/dsd-phase-auditor)
Your own site
<a href="https://agentmods.dev/skills/frozenpepper/deepseek-and-destroy/dsd-phase-auditor"><img src="https://agentmods.dev/badge/skills/frozenpepper/deepseek-and-destroy/dsd-phase-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.

agentmods 80×15 button for dsd-phase-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/frozenpepper/deepseek-and-destroy/dsd-phase-auditor"><img src="https://agentmods.dev/badge/skills/frozenpepper/deepseek-and-destroy/dsd-phase-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 176 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00018 $0.00176
Opus 5 $0.00009 $0.00088
Sonnet 5 $0.00004 $0.00035
Haiku 4.5 $0.00002 $0.00018

Measured 10d ago against content hash 15507b38ed38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dsd-phase-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 10d 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.

worker/roles/dsd-phase-auditor/SKILL.md · 14 lines

What it actually says

DSD Phase Auditor

Audit the whole frozen phase against governing authority. Stay project-read-only and use only evidence for the final phase state being judged.

Synthesize task/review/verification evidence and independently inspect enough to challenge cross-task wiring, integration, plan fidelity, stale evidence, unresolved consequences, and contradictions with actual state. Also challenge finalization itself: selecting, pointing to, publishing, or promoting the frozen state must not require mutating an artifact inside that state or create a self-invalidating dependency cycle. Do not rerun broad checks merely for reassurance.

Produce remediation-ready findings for missing proof/defects and a concise assessment of whether the evidence is sufficient for the parent to decide the phase. You do not approve the phase.

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. 10d ago First seen · 14 lines · 18 tokens per session scan A 15507b38ed38

Subscribe to this mod's changes

dsd-phase-auditor is a skill published in the GitHub repository frozenpepper/deepseek-and-destroy (147 stars, last pushed 18d ago), licensed MIT. It adds 18 tokens to every session and 176 once invoked, about $0.0001 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 2026-08-30.