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 randommonicle/claude-skills --skill enforce-invariants-in-buildgit clone --depth 1 https://github.com/randommonicle/claude-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/randommonicle/claude-skills/enforce-invariants-in-build)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/enforce-invariants-in-build"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/enforce-invariants-in-build/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/randommonicle/claude-skills/enforce-invariants-in-build"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/enforce-invariants-in-build.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 | $0.00106 | $0.00662 |
| Opus 5 | $0.00053 | $0.00331 |
| Sonnet 5 | $0.00021 | $0.00132 |
| Haiku 4.5 | $0.00011 | $0.00066 |
Grade A, and why
enforce-invariants-in-build 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 12d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enforce invariants in the build
Three-repo convergence. A file declaring itself "the ONLY place model names appear" had zero importers and pinned stale model ids — dead code that looked authoritative. A safety carve-out ("never auto-N/A the lifts section") was enforced only by the absence of a line and regressed silently for five weeks. A design guarantee ("only field X crosses the boundary") had no code behind it. The counter-example that proves the pattern: a config kept honest by a byte-identical unit test never drifted.
The rule
When prose asserts an invariant, ask: can a violation exist without failing the build? If yes, back the invariant with a mechanism — a test, a constraint, a trigger, a lint rule — or delete the assertion. A documented lesson is not a control; only a mechanical step prevents recurrence.
How to apply
- Grep any file that declares its own authority. "The single source of truth for X" is verified by counting its importers; zero importers means the claim is not just false but misleading — dead code that pins external identifiers is worse than ordinary dead code.
- A deliberate duplicate needs a byte-identical test so divergence is a red build, not a discovery.
- A safety carve-out needs a named, tested rule. Encode "never auto-X" as a function
(
autoNaCandidates()style) plus a test asserting the unsafe state cannot occur — never as the absence of a line someone can helpfully add back. - "These must match" needs a drift check — a zero-rows query, a checksum, a CI comparison — per blast-radius-grep's denormalisation rule.
- On finding an unenforced invariant in existing code, add the mechanism in the same change or flag it per flag-deferred-items; do not add another sentence of prose.
What this skill does not do
It does not track deferred work (flag-deferred-items) and does not write the tests themselves (prove-it-can-fail governs their integrity). It converts assertions into mechanisms.
Why
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.
- 12d ago First seen · 49 lines · 106 tokens per session scan A 540713b0cd71
enforce-invariants-in-build is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 106 tokens to every session and 662 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.