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 jongwony/epistemic-protocols --skill reduced-space-testgit clone --depth 1 https://github.com/jongwony/epistemic-protocolsWrote 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/jongwony/epistemic-protocols/reduced-space-test)<a href="https://agentmods.dev/skills/jongwony/epistemic-protocols/reduced-space-test"><img src="https://agentmods.dev/badge/skills/jongwony/epistemic-protocols/reduced-space-test/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/jongwony/epistemic-protocols/reduced-space-test"><img src="https://agentmods.dev/badge/skills/jongwony/epistemic-protocols/reduced-space-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.03576 |
| Opus 5 | $0.00021 | $0.01788 |
| Sonnet 5 | $0.00008 | $0.00715 |
| Haiku 4.5 | $0.00004 | $0.00358 |
Grade A, and why
reduced-space-test 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reduced-Space Test: Scoped Empirical Validation
Validate an inference-uncertain proposition inside a constraint-bounded stand-in space synchronized with the user, obtain a scoped resolution ("within these conditions, whether it holds, fails, or remains inconclusive"), and carry the uncovered complement forward to a follow-up protocol. This skill does not run the experiment substrate, open branches, or create PRs. It orchestrates existing protocols around one disciplined empirical move.
This is an orchestration utility, not a runtime executor and not a new epistemic protocol. Reduced-Space Test introduces no new interaction deficit. It realizes a known composite — decompose the target↔surrogate equivalence claim into verifiable facets, then /bound a synchronized test space (+ residual) ∘ /inquire for evidence inside it → scoped resolution + carried complement. It is sibling to /triage and /forge: a thin composition over existing protocols, kept outside the core protocol set because it owns no deficit of its own.
The core recognition act is decomposing the equivalence claim into verifiable facets — not "creating a reduced space." A stand-in space is only as good as the facets on which it is claimed equivalent to the target; the value lives in making those facets explicit and observable.
Core Contract
/reduced-space-test owns scoped empirical validation:
InferenceUncertainClaim
-> ScopedClaimFrame (core: decompose target↔surrogate equivalence into verifiable facets)
-> BoundedTestSpace (/bound: user-synchronized in-scope space + residual complement)
-> EmpiricalEvidence (/inquire: observe inside the bounded space, evidence over inference)
-> ScopedResolution | CoverageShortfall (scoped outcome — holds, fails, or inconclusive — within the claim's defined conditions; or, on under-coverage, a CoverageShortfall: slice-scoped resolution or no resolution, with the remainder re-bounded or carried)
-> Residual (uncovered complement -> follow-up protocol)
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 · 139 lines · 42 tokens per session scan A 484a8163d4a9
reduced-space-test is a skill published in the GitHub repository jongwony/epistemic-protocols (161 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 3,576 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 2026-08-30.
Other skills, from other repositories
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.
taiyi-test
A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.
flow-next-qa
Live-app QA pass derived from the spec. Drives the running app, files P0/P1/P2 findings with evidence, emits a YES or NO qaverdict receipt.
flow-next-features
Seed or maintain the committed user-POV drive map at .flow/features/ so QA and drive reuse how a user reaches each feature.
maestro-work
Drive one accepted implementation unit - smallest falsifiable behavior, minimum edits, evidence that names the real falsifier; red tests only inside a Full bundle.
review-core-correctness
Normative mandatory reviewer for correctness, contracts, architecture sanity, UX behavior, code quality and tests in the explyt spring-plugin codebase. Use during orchestrated code review of a PR, diff, commit or branch, or when asked to review correctness, logic, architecture or test coverage of plugin changes.