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.
npx skills add synaptiai/synapti-marketplace --skill gap-and-contradiction-registergit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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.
[](https://agentmods.dev/skills/synaptiai/synapti-marketplace/gap-and-contradiction-register)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
- 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.
- Run a safe check the action ceiling permits. An executed command answers what a document may only assert.
- Ask a concise, evidence-seeking question — only if a person genuinely must resolve it, and only when
allowedActions.contactHumansis 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?" - Otherwise mark the affected claims and documents unresolved and continue.
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.
- 9d ago First seen · 121 lines · 144 tokens per session scan A 6428d82ec3dd
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.
Other skills, from other repositories
step4-archive-spec
Archive a completed spec — moves it to specs-archived and blocks agent access.
plan-roadmap
Create or update a prioritized product roadmap with phased milestones.
x-dev
A development workflow for completing tasks from a task folder. It follows the task's README and checklist, implements work in dependency order, and records verification evidence.
x-req
A requirements planner that turns a confirmed request into a ready-to-build task package. It assigns a risk level from Q0 to Q3, where higher levels cover changes such as permissions, public interfaces, data migrations, or concurrency.
pocket-closing
Terminal pocket stage. User invokes after pocket-development's phase-level pass writes verdicts. Reconciles reviews against log.json, gates on REVIEWFAIL/REVIEWBLOCKED, advances REVIEW→DONE, runs log close, and emits a closeout summary. Trigger on "pocket-closing", "close the plan", "close out", "finalize plan", or…
product-manager
Use when writing user stories or acceptance criteria, defining product requirements, prioritising a feature backlog, creating a product roadmap, analysing product metrics, facilitating discovery for a new feature, evaluating trade-offs between product directions, or any task that requires deciding what to build and…