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 jleechanorg/agent-orchestrator-ts --skill skeptic-agentgit clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-tsWrote 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/jleechanorg/agent-orchestrator-ts/skeptic-agent)<a href="https://agentmods.dev/skills/jleechanorg/agent-orchestrator-ts/skeptic-agent"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/skeptic-agent/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/jleechanorg/agent-orchestrator-ts/skeptic-agent"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/skeptic-agent.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 | $0.00025 | $0.01162 |
| Opus 5.5 | $0.00010 | $0.00465 |
| Sonnet 5.5 | $0.00005 | $0.00232 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
skeptic-agent 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skeptic Agent — Exit Criteria Verification
When This Skill Activates
Proactively activate when:
- User requests a non-trivial task (multi-file, multi-step, integration work)
- User asks to "build", "implement", "fix", or "migrate" something that will take >10 tool calls
- Task involves E2E verification, pipeline work, or multi-system coordination
- User invokes
/skepticor asks for skeptic verification
Before starting the task, ask:
"This looks non-trivial. Want to define skeptic exit criteria? A separate agent will independently verify these when you think you're done. What does 'actually done' look like for this task?"
If the user declines, proceed without. If they define criteria, save them to specs/exit-criteria.md in the workspace.
How It Works
1. Define Exit Criteria (human writes, at task start)
# specs/exit-criteria.md
## Task: [task name]
### Criterion A: [name]
What to verify: [natural language description]
Command to run (if applicable): [exact command]
What PASS looks like: [expected output/state]
What FAIL looks like: [common proxy substitutions to watch for]
### Criterion B: [name]
...
2. Coder Works (normal agent session)
The coding agent works normally. It does NOT see specs/exit-criteria.md.
It signals readiness by stating "I believe the task is complete" or similar.
3. Skeptic Evaluates (separate session, different model if possible)
When the coder signals completion, spawn or switch to a skeptic session. The skeptic's system instructions:
You are a QA Skeptic. Your job is to FIND GAPS in the implementation.
INVERTED INCENTIVE: You are rewarded for finding missing evidence.
A false PASS is YOUR failure. A thorough FAIL report is success.
Rules:
1. Read specs/exit-criteria.md
2. For each criterion, run the EXACT verification specified
3. Do NOT accept the coder's claims — verify independently
4. Unit tests do NOT satisfy E2E criteria
5. Manual tool calls do NOT satisfy pipeline criteria
6. "Code compiles" does NOT mean "feature works"
7. EVIDENCE MUST BE VIDEO: For UI and interactive terminal criteria, ONLY accept .gif, .mp4, .webm, or .mov videos (UI) or .gif, .mp4, .webm, .mov, .cast (terminal) tied to a commit SHA. Static screenshots FAIL — no exceptions.
Output format per criterion:
CRITERION: [quote verbatim from specs/exit-criteria.md]
EVIDENCE FOUND: [what you actually observed — commands run, output seen]
EVIDENCE MISSING: [what should exist but doesn't]
VERDICT: PASS | FAIL | INSUFFICIENT
REASON: [specific gap or confirmation]
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 · 133 lines · 25 tokens per session scan A d6e670683da7
skeptic-agent is a skill published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 1,162 once invoked, about $0.0001 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 2026-10-02.
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.