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 easyinplay/harnessed --skill paranoidgit clone --depth 1 https://github.com/easyinplay/harnessedWrote 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/easyinplay/harnessed/paranoid)<a href="https://agentmods.dev/skills/easyinplay/harnessed/paranoid"><img src="https://agentmods.dev/badge/skills/easyinplay/harnessed/paranoid/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/easyinplay/harnessed/paranoid"><img src="https://agentmods.dev/badge/skills/easyinplay/harnessed/paranoid.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 | $0.00131 | $0.01450 |
| Opus 5.5 | $0.00052 | $0.00580 |
| Sonnet 5.5 | $0.00026 | $0.00290 |
| Haiku 4.5 | $0.00013 | $0.00145 |
Grade A, and why
verify-paranoid 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-paranoid workflow (v3)
Overview
1-phase sub-workflow mapping CLAUDE.md "gstack 治理关卡 🔒 关键模块 PR 前强制 — /review"
onto harnessed runtime (Phase v3.0-3.4 W0.12 — D-04 Stage ④ Verify 7 sub + D-12 gstack
治理关卡 + Pattern A sub-workflow ship)。
| phase | id | upstream | model | capability | gate |
|---|---|---|---|---|---|
| 1 | 01-review |
gstack | opus | {{ capabilities.gstack-review.cmd }} |
judgments.stage-routing.verify-paranoid-critical.fires |
Per-phase config loads from workflows/verify/paranoid/workflow.yaml; engine 4-level gate
resolver evaluates phase.is_critical_module == true via expr-eval — true 则 invoke gstack
/review, false 则 skip (chain_isolation 3 铁律 R20.16 sister verify-work v2 phase 04)。
Capability refs
Sister workflows/capabilities.yaml entries:
gstack-review— Bucket 3 治理关卡 (impl: gstack, cmd: /review, fires_when: phase.is_critical_module == true)
Gate ref
Sister workflows/judgments/stage-routing.yaml:
verify-paranoid-critical.fires—phase.stage == 'verify' and phase.is_critical_module == true(默认 critical fire only; 普通 PR 应跳过 — gstack-review 是 Paranoid Staff Engineer 重武器)
Routing rules (sister CLAUDE.md "gstack 治理关卡")
- ✅ 触发: 关键模块 PR 前 (auth / payment / data migration / core algorithm 等)
- ❌ 跳过: 常规 PR / docs / config / 非核心 module
How to invoke
!harnessed checkpoint intent verify-paranoid
The banner above (when present) means this invocation is REGISTERED with the engine (an intent marker) — not yet compliant: the steps below (prompt → spawn → checkpoint complete) resolve it, and a per-turn
<workflow-intent>reminder persists until they run.
The numbered sequence below is the state machine — execute it with Bash. Do NOT improvise an equivalent flow from the Overview above: freelancing bypasses the engine (no ledger, no evidence guard). harnessed gives you the spawn-ready prompt; YOU spawn the subagent with a {{ host.native }} {{ host.spawn_subagent }} (keeps the session responsive + lets clarification round-trips reach the user).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · -1 lines 8694ce58a826
- 2mo ago First seen · 86 lines · 131 tokens per session scan A 931fa6f89812
verify-paranoid is a skill published in the GitHub repository easyinplay/harnessed (2 stars, last pushed today), licensed Apache-2.0. It adds 131 tokens to every session and 1,450 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
security-architecture-review
Reviews a design or change for security before it ships — authentication and authorization, data handling, secrets, dependencies, and the secure-development practices around it. Use this to review an architecture or pull request for security, set secure coding standards, choose or tune SAST and DAST tooling, assess a…
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.