Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Dr Audit Spec Drift

ASecurity

Audit dimension - find where the code deviates from the spec series and where shipped surface is spec-silent, by a two-direction term census. Invoked by dr-audit-orchestrator when spec-drift.md is missing.

142 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agents

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add AHepi/DeepReason --skill dr-audit-spec-drift --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dr Audit Spec Drift?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Dr Audit Spec Drift
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ahepi-dr-audit-spec-drift/badge)](https://www.skillsdirectory.com/skills/ahepi-dr-audit-spec-drift)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: dr-audit-spec-drift
description: Audit dimension - find where the code deviates from the spec series and where shipped surface is spec-silent, by a two-direction term census. Invoked by dr-audit-orchestrator when spec-drift.md is missing.
---

# Audit: code vs spec

Entry: `LEDGER.md` exists, `spec-drift.md` missing. Exit:
`spec-drift.md` written, LEDGER rows added, proofs in `proof/`.

Two directions, both mechanical:
- SPEC→TREE: a term the spec names that the tree no longer honors =
  the code deviates from spec.
- TREE→SPEC: a shipped public surface the spec never mentions = the
  spec is behind the code.

The spec series is every `docs/harness-spec-*.md` (base + all
amendments — read ALL amendments; later files supersede earlier ones
on conflict, so verify a term against the newest file naming it).

## Operations

1. SPEC term census:
   `rg -o -N '\x60[A-Za-z_][A-Za-z0-9_.:-]*\x60' docs/harness-spec-*.md | sort -u > proof/spec-terms.txt`
   plus every `##`-level heading noun phrase. This is the SPEC list.
2. For each SPEC term: `rg -l -w '<term>' src/deepreason/` (identifiers)
   or `rg -l '<term>' src/ docs/map/` (concept phrases). Zero hits →
   verdict `spec-orphan` (spec names it, tree does not have it), one
   row each with the scan saved. Hits → tally only.
3. TREE surface census, three lists with proofs:
   a. CLI flags: `rg -o -N '"--[a-z][a-z0-9-]*"' src/deepreason/cli/main.py | sort -u`
   b. Config fields: `rg -o -N '^    [A-Z][A-Z0-9_]*:' src/deepreason/config.py | sort -u`
   c. Typed error/refusal strings: `rg -o -N '"[A-Z][A-Z0-9_]{6,}"' src/deepreason/run_manifest.py src/deepreason/preparation.py | sort -u`
4. For each TREE surface item: `rg -l -F '<item>' docs/harness-spec-*.md`.
   Zero hits → verdict `spec-silent` (shipped, undocumented in spec),
   one row each. Batch rows by feature, not per flag, when one tranche
   shipped them together (the row names the batch and lists members).
5. Write `spec-drift.md`: two tables (one per direction) with count
   lines. The `spec-silent` table's parked prompt is a spec-amendment
   draft request (append-only amendment file, never an edit to
   existing spec text), route dr-change-orchestrator.

## GATE

Pass: proofs exist for both censuses; every `spec-orphan` and every
`spec-silent` row cites its scan file; count lines match row counts.
Verdict labels: `spec-orphan` | `spec-silent` | `covered`.

## Activation plant (first run)

Append a fabricated term row to the SPEC list copy in
`proof/spec-terms.txt`; step 2 must produce a `spec-orphan` verdict
for it (zero hits). Delete the fabricated row, note the plant in
ACTIVATION.md.

## Outlets

| Situation | Outlet |
|---|---|
| Impulse to draft the amendment now | PARK — amendment prompt, route dr-change-orchestrator |
| A spec term superseded by a newer amendment | verdict `covered`, row notes the superseding file |
| Term ambiguous between identifier and concept | run both scan shapes, row the weaker result, save both proofs |

Attribution

AHepiAHepi
View sourceMore from AHepi →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →