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 gustavo-meilus/superpipelines --skill run-parity-test-hgit clone --depth 1 https://github.com/gustavo-meilus/superpipelinesWrote 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/gustavo-meilus/superpipelines/run-parity-test-h)<a href="https://agentmods.dev/skills/gustavo-meilus/superpipelines/run-parity-test-h"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/run-parity-test-h/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/gustavo-meilus/superpipelines/run-parity-test-h"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/run-parity-test-h.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 | $0.00044 | $0.02436 |
| Opus 5 | $0.00022 | $0.01218 |
| Sonnet 5 | $0.00009 | $0.00487 |
| Haiku 4.5 | $0.00004 | $0.00244 |
Grade A, and why
run-parity-test-h 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 11d 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.
This is a copy
92% identical to run-parity-test-g — 99 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
run-parity-test-h — Entry Skill
Entry point for the
parity-test-hpipeline. Orchestrates the sequential inline execution of thevalidator,reviewer, andreporterprotocol steps on Tier 2 (Cursor/Windsurf/Cline). All steps execute in this skill's session — no subagents, no Task() calls.
Platform Context
- Tier:
tier_2(Cursor/Windsurf/Cline) - Dispatch mechanism:
inline— noTask()primitive, no subagent processes. All three steps execute within this skill's session. - model_field_format:
omit— nomodel:field is emitted for any step. The host IDE owns model selection. - Reviewer isolation:
convention— no structural isolation. C19 self-skepticism preamble required in the reviewer protocol. - Degradation warnings: 3 active (see PHASE 0 below).
Workflow
PHASE 0: PREFLIGHT — DEGRADATION WARNINGS AND INITIALIZATION
Step 0.1 — Surface Tier 2 degradation warnings (MANDATORY before any execution):
Surface ALL of the following warnings to the user verbatim before any other action:
[Tier 2 Degradation Warning 1 of 3] Reviewer isolation impossible on this platform: writer and reviewer are the same agent in the same context. Review steps execute the reviewer protocol but cannot provide assumption-blindness defense or context-bleed isolation. Treat review output as a self-check, not verification.
[Tier 2 Degradation Warning 2 of 3] Parallel fan-out (Pattern 2) requires worktrees and is unavailable on this platform (worktrees: false).
[Tier 2 Degradation Warning 3 of 3] Model selection is owned by the host IDE; per-step model assignment is not emitted.
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.
- 11d ago First seen · 209 lines · 44 tokens per session scan A a84d1962abc9
run-parity-test-h is a skill published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 2,436 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to run-parity-test-g, differing in 99 lines, and is treated as a copy.
Other skills, from other repositories
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
refactor
Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.
prompt-caching-patterns
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Triggers: prompt caching, cachecontrol, cache breakpoint, cache TTL, hit rate.