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 abstractonion/cadence --skill no-hacking-central-infragit clone --depth 1 https://github.com/abstractonion/cadenceWrote 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/abstractonion/cadence/no-hacking-central-infra)<a href="https://agentmods.dev/skills/abstractonion/cadence/no-hacking-central-infra"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/no-hacking-central-infra/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/abstractonion/cadence/no-hacking-central-infra"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/no-hacking-central-infra.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 | $0.00048 | $0.00358 |
| Opus 5 | $0.00024 | $0.00179 |
| Sonnet 5 | $0.00010 | $0.00072 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
no-hacking-central-infra 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.
What it actually says
Don't hack central infra to make tests pass
When a test, eval, or local run fails, fix it at the edges — in the test, the fixture, the feature code under test — not by reaching into shared settings, base classes, middleware, or framework-level configuration.
Why
Central infra changes have blast radius far beyond the failing test. A toggle that makes the failure go away usually masks the real cause, breaks other tests subtly, or leaks into production behavior. The signal you'd have gotten from the failure is lost.
What counts as "central infra"
- Settings modules / environment configuration (
settings.py,config/*,.env.test). - Base classes / mixins that every model, view, or test inherits from.
- Middleware, auth backends, request/response hooks.
- Shared conftest fixtures used by many test files.
- ORM defaults, signal handlers, cache backends, queue plumbing.
Do instead
- Fix the test or its local fixture if the failure is test-specific.
- Fix the feature code if the test is correct and the code is wrong.
- Add a narrowly-scoped override (e.g.
@override_settingsfor one test) rather than mutating the global default.
When central infra really is the root cause
Say so explicitly. Propose the change as its own focused commit with a justification — not bundled into the test/feature work. The user should agree the change belongs at the infra level before it lands.
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 · 31 lines · 48 tokens per session scan A e9b2f8e8e20a
no-hacking-central-infra is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 358 once invoked, about $0.0002 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.