bidirectional-differential

bidirectional-differential is a skill for Claude Code from jszmajda/lid. It costs 172 tokens per session (2,571 once invoked), scanned B, original, MIT.

A review that compares a feature's written requirement with its code in both directions. EARS is a structured format for writing software requirements.

In plain words
What is it for?
Use it for a differential audit of EARS-to-code pairs, including the /differential-audit command or the workflow's completion checkpoint.
Why use it?
It reveals where code no longer matches the requirement, or where the requirement cannot be reconstructed from the code, so people can focus their review.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the lid-experimental plugin — 1 skill, 1 command shipped together

Good fit Use it for a differential audit of EARS-to-code pairs, including the /differential-audit…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jszmajda/lid/bidirectional-differential
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 jszmajda/lid --skill bidirectional-differential
Clone the repo
git clone --depth 1 https://github.com/jszmajda/lid

Made for: Claude Code.

Or install lid-experimental, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 bidirectional-differential

README.md
[![agentmods](https://agentmods.dev/badge/skills/jszmajda/lid/bidirectional-differential.svg)](https://agentmods.dev/skills/jszmajda/lid/bidirectional-differential)
Your own site
<a href="https://agentmods.dev/skills/jszmajda/lid/bidirectional-differential"><img src="https://agentmods.dev/badge/skills/jszmajda/lid/bidirectional-differential.svg" alt="Measured on agentmods" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00172 $0.02571
Opus 5 $0.00086 $0.01286
Sonnet 5 $0.00034 $0.00514
Haiku 4.5 $0.00017 $0.00257

Measured 7d ago against content hash 8d10cbc26d21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

bidirectional-differential scanned grade B with 1 finding 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 7d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**Do not mutate existing per-arrow overlay files** (`docs/arrows/{segment}.md`, `docs/arrows/index.yaml`). Experiment artifacts stay in the reserved subtree so arrow-maintenance's audit loop can ignore them. Retirement o

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/lid-experimental/skills/bidirectional-differential/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bidirectional Differential

This skill runs a bidirectional differential audit on EARS↔code pairs. The audit is advisory — findings concentrate human review on specific cases, and acting on findings is always user-judged. When the audit surfaces drift, the recommended repair path walks the whole arrow: validate intent with the user, then cascade EARS → Tests → Code.

When to act

Command mode — user invokes /differential-audit:

  • No arguments → open the scoping conversation (see §Scoping).
  • One or more EARS IDs as arguments → audit them directly with configured defaults; skip the scoping conversation.

Ambient mode — at linked-intent-dev's Phase 6 boundary (code is complete for a change) in a project where arrow-maintenance's overlay exists and ambient triggering is not disabled. Emit one batched prompt listing every EARS the change touched, offering all, none, a comma-separated subset, or skip-arrow. If ambient is disabled in the project's CLAUDE.md (see §Configuration), do not fire.

Ambient mode is advisory: declining, skipping, or any classification outcome MUST NOT block Phase 6 completion.

Hard precondition — arrow-maintenance overlay

Before spawning any blind sessions in either mode, verify the arrow-maintenance overlay exists:

  • docs/arrows/index.yaml present, and
  • at least one per-arrow overlay file under docs/arrows/.

If absent, abort with:

Bidirectional differential audits attach to the arrow-maintenance overlay. Run /update-lid and then /arrow-maintenance first to establish the arrow surface this skill extends.

Do not spawn any claude -p sessions and do not write any files when the overlay is absent. This skill is heavier maintenance than arrow-maintenance; a project without the lighter layer in place will not act on this skill's findings either.

Scoping

The scoping conversation is the first user-facing moment. The audit itself runs without further input once scope is fixed. Full script in references/scoping-conversation.md.

Read the full file on GitHub · 130 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 130 lines · 172 tokens per session scan B 8d10cbc26d21

Subscribe to this mod's changes

bidirectional-differential is a skill published in the GitHub repository jszmajda/lid (101 stars, last pushed 25d ago), licensed MIT. It adds 172 tokens to every session and 2,571 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

moai-foundation-quality

TRUST 5 quality principles and how MoAI enforces them through agents, the 3-level harness, /moai gate, and sync-auditor scoring. Use for code review, quality gate checks, coverage targets, or TRUST 5 compliance.

modu-ai/moai-adk · 58 tokens

test-strategy

Coverage-design method for qa-engineer — pyramid ratios per archetype, equivalence/boundary/property case selection, mutation score as the real coverage signal, and a flake-quarantine policy. Turns "coverage is 90%" (a number with no method) into a defensible test plan. Emits TEST-STRATEGY-{slug}.md, which the QA gate…

avelikiy/great_cto · 82 tokens

quant-validation

The methods a financial-ML result has to survive before it is evidence — purged cross-validation with an embargo, triple-barrier labelling, sample uniqueness under overlapping labels, fractional differentiation, meta-labelling, and multiple-testing correction. Written because the invariants were required of…

avelikiy/great_cto · 104 tokens

reviewer

Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…

qwerfunch/cladding · 68 tokens

refactor

Structured refactoring runner with ETAP workflow, resumable CONTRACT, and batch processing. Use when restructuring code, extracting methods, splitting files, breaking circular dependencies, or cleaning up god classes. NOT for new features (use zuvo:build). Execution modes: full (default), batch (queue processing).…

greglas75/zuvo · 79 tokens

mutation-test

Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…

greglas75/zuvo · 190 tokens