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 tmusser/ai-engineering-skills --skill falsify-specgit clone --depth 1 https://github.com/tmusser/ai-engineering-skillsWrote 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/tmusser/ai-engineering-skills/falsify-spec)<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/falsify-spec"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/falsify-spec/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/tmusser/ai-engineering-skills/falsify-spec"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/falsify-spec.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 | $0.00034 | $0.01038 |
| Opus 5.5 | $0.00014 | $0.00415 |
| Sonnet 5.5 | $0.00007 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
falsify-spec 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Falsify Spec
Purpose
Find the plausible wrong implementation that still passes the written spec. Pressure-test acceptance criteria before coding, not the code after it ships.
This is an optional adversarial pass between mini-spec and implementation.
It does not replace source grooming, the deterministic spec_gate.py auditability
check, test-mini, or post-implementation verify-contract.
When to use
Invoke as /falsify-spec or ask "What wrong implementation could pass this spec?"
Use selectively when a spec is written but an ambiguous boundary, regression
seam, data meaning, or potentially weak acceptance test could produce false
confidence. Skip when the slice is trivial and already unambiguous.
Do not activate merely because mini-spec ran or the skill is installed.
If a usable spec does not exist yet, write one with mini-spec first.
Inputs
- Current
SPEC.mdwith acceptance criteria, non-goals, invalid-if constraints, verification demo, and any declared authoritative references - Original user request and directly relevant tests, schemas, code, or fixtures
- Named compatibility seams and any known baseline behavior
Workflow
- Read authority narrowly. Inspect
SPEC.md, the original request, and only sources that govern the candidate boundary. Record discrepancies; source silence is not evidence of an intended requirement. - Pick at most three high-consequence targets. Prefer criteria that could pass shallow tests while breaking the user's intended outcome, a preserved behavior, or a named non-goal. Do not generate a generic test checklist.
- Construct a concrete counterexample. For each target, name a plausible implementation, an input or state, and its observable output. Explain which written acceptance criterion/test it passes and what intended behavior it would violate. If it cannot plausibly pass, discard it.
- Classify the basis. A counterexample is
SOURCE_BACKEDonly when the violated expectation has a locator in the request or a governing source. Otherwise label itHYPOTHESIS, not a proven defect or new requirement. - Find the smallest discriminator. Propose one precise acceptance-criterion delta and, when feasible, one focused negative/regression test or manual probe that rejects the counterfeit while allowing valid behavior. Keep original source semantics, scope ceilings, permissions, and existing tests intact.
- Resolve ownership correctly. For
SOURCE_BACKEDgaps, recommend updating the existingSPEC.mdand proof target before implementation. ForHYPOTHESISgaps that require a product choice, markDECISION_REQUIRED; do not silently turn them into acceptance criteria. - Stop. Report at most three counterexamples in a single compact response.
If explicitly authorized, amend the existing spec; otherwise propose the
exact delta for the operator to accept. Do not create
FALSIFICATION.md, a second contract, or a mandatory new workflow stage.
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.
- 5d ago First seen · 100 lines · 34 tokens per session scan A 49b2ac0ec794
falsify-spec is a skill published in the GitHub repository tmusser/ai-engineering-skills (6 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 1,038 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
code-review
Use this skill to systematically review code changes for correctness, security, performance, maintainability, and test coverage. Activates after implementation, before merging, or when asked to review a pull request or code change. Produces a structured review report with findings categorized by severity.
tdd
Use this skill to practice test-driven development — writing tests before implementation, using tests to drive design, and validating implementation against pre-written tests. Activates when implementing new functionality, refactoring code, or fixing bugs where regression coverage is needed.
bug-diagnosis
Use this skill to systematically diagnose the root cause of a bug before attempting a fix. Activates when a bug is reported, a test is failing, or unexpected behavior is observed. Prevents guess-and-check debugging that introduces additional bugs while chasing symptoms.
skill-release-gate
Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.
mcore-testing
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.