gap-and-contradiction-register

gap-and-contradiction-register is a skill for Claude Code from synaptiai/synapti-marketplace. It costs 144 tokens per session (1,849 once invoked), scanned A, original, Apache-2.0.

A register for recording missing information, assumptions, open questions, and disagreements between sources. It separates issues that block work from issues that do not.

In plain words
What is it for?
It is for tracking documentation gaps, unresolved questions, source contradictions, and their effect on project decisions.
Why use it?
It prevents uncertain or conflicting information from being quietly treated as fact. Teams can see what needs an owner or a decision.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Part of the dossier plugin — 10 skills, 9 commands, 6 agents, 2 hooks shipped together

Good fit It is for tracking documentation gaps, unresolved questions, source contradictions, and their effect on project decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synaptiai/synapti-marketplace/gap-and-contradiction-register
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 synaptiai/synapti-marketplace --skill gap-and-contradiction-register
Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install dossier, the plugin that ships this one along with the rest of its 10 skills, 9 commands, 6 agents, 2 hooks.

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 gap-and-contradiction-register

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/gap-and-contradiction-register/github.svg)](https://agentmods.dev/skills/synaptiai/synapti-marketplace/gap-and-contradiction-register)
Your own site
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/gap-and-contradiction-register"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/gap-and-contradiction-register/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 gap-and-contradiction-register

Your own site · 80×15
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/gap-and-contradiction-register"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/gap-and-contradiction-register.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,849 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.
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 $0.00144 $0.01849
Opus 5 $0.00072 $0.00924
Sonnet 5 $0.00029 $0.00370
Haiku 4.5 $0.00014 $0.00185

Measured 9d ago against content hash 6428d82ec3dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gap-and-contradiction-register 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 9d 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.

plugins/dossier/skills/gap-and-contradiction-register/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gap and Contradiction Register

Owns what the package does not know, and where its sources disagree. The evidence ledger asserts; this register refuses to.

Iron Law

NEVER RESOLVE A CONTRADICTION BY CHOOSING. Record both sides, name the decision impact, escalate to the owner.

Picking the more convenient version is the single most damaging thing a documentation run can do, because the result is indistinguishable from a verified fact and carries the same authority.

Two registers

Register ID Records
Assumptions and open questions AQ-#### Something required is not established: a silent source, an inaccessible system, an unstated owner, an assumption the package rests on
Contradictions CT-#### Two or more sources disagree about the same claim

Both live in one file because they answer the same reader question — "what is not settled here?" — and splitting them buries half the answer.

Column schemas and ID grammar: references/register-schemas.md.

Gap classification

Classify on decision impact, not on effort to resolve.

Class Definition Effect on the run
Blocking Documentation would materially mislead a reader without resolution Drafting of the affected document stops. Everything else continues
Material, non-blocking The package can proceed with a visible qualification in the affected document Draft with the qualification inline; the row stays open
Minor Useful refinement, not decision-changing Record it, draft normally

Do not stall the entire package for a non-blocking unknown. A package delivered with twelve honest open questions is more useful than a package delayed indefinitely for one of them.

Before escalating a blocking gap

In this order. Escalation is the last step, not the first.

  1. Search again by a different route. A different search term, a different directory, git history, a schema, a test fixture, a configuration default. Most gaps are findable, and the first search was one route.
  2. Run a safe check the action ceiling permits. An executed command answers what a document may only assert.
  3. Ask a concise, evidence-seeking question — only if a person genuinely must resolve it, and only when allowedActions.contactHumans is true. Ask for the specific artifact, not for an explanation: "Is there an approved data-retention record for the analytics store?" beats "Can you explain how retention works?"
  4. Otherwise mark the affected claims and documents unresolved and continue.

Read the full file on GitHub · 121 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. 9d ago First seen · 121 lines · 144 tokens per session scan A 6428d82ec3dd

Subscribe to this mod's changes

gap-and-contradiction-register is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 144 tokens to every session and 1,849 once invoked, about $0.0007 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 2026-09-03.

Related

Other skills, from other repositories