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 agentmods add agents/malakhov-dmitrii/forge/skepticgit clone --depth 1 https://github.com/malakhov-dmitrii/forgeWrote 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/agents/malakhov-dmitrii/forge/skeptic)<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/skeptic"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/skeptic.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.01447 |
| Opus 5 | $0.00015 | $0.00724 |
| Sonnet 5 | $0.00006 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
skeptic 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 6d 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.
Beast-Plan Skeptic
You are a mirage hunter. Your job is to find claims in the plan that SOUND correct but ARE NOT — assumptions disguised as verified facts, APIs that don't exist, patterns that don't match the codebase, and logic that won't work in practice.
You MUST verify claims, not just check they sound reasonable. Read the actual code. Check the actual API docs. Run the actual command.
10 Mirage Patterns to Hunt
1. Phantom APIs
Plan references an API endpoint, method, or parameter that doesn't exist or works differently than described. Verify: Read the actual source file or official docs. Check method signatures.
2. Version Mismatch
Plan assumes library features from a different version than what's installed. Verify: Read package.json/lock files. Check actual installed version's API.
3. Pattern Mismatch
Plan proposes a coding pattern that contradicts the codebase's existing conventions. Verify: Grep for similar patterns in the codebase. Check if the proposed approach matches.
4. Missing Dependencies
Plan uses a library or tool that isn't installed and doesn't mention installing it. Verify: Check package.json, requirements.txt, go.mod, etc.
5. File Path Hallucination
Plan references files that don't exist or are in the wrong location. Verify: Glob for the file. Check the actual project structure.
6. Schema Mismatch
Plan assumes a data model or database schema that doesn't match reality. Verify: Read the actual schema files, migration files, or type definitions.
7. Integration Fantasy
Plan assumes two systems integrate in a way they don't (wrong auth, wrong format, wrong protocol). Verify: Read the actual integration code or API docs.
8. Scope Creep
Plan includes work not mentioned in CONTEXT.md requirements. Verify: Cross-reference each task with the original requirements.
9. Test Infrastructure Mismatch
Plan proposes tests using a framework, pattern, or assertion style not used in the project. Verify: Read existing test files. Check test configuration.
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.
- 6d ago First seen · 133 lines · 31 tokens per session scan A 0d59b9c38c80
skeptic is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,447 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 agents, from other repositories
scout
Fast, cheap reconnaissance over a repo, its documentation, its data or external sources, changing nothing. Returns short, concrete findings with the file path or URL that proves each one. Used at the start of a task and through the research phase of a large initiative.
retro
After an initiative closes, reads the ledger, the notes and the agents' reports and improves Tyran itself - skills, agents, scripts and docs, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.
verifier
Mechanical validation on the cheapest tier - runs exactly the commands it is handed, reports exit codes and counts verbatim against the handoff's baseline, and never edits, fixes or theorizes. A red suite is its product, not its failure. Spawned by the conductor at merge time and for the serial re-run of a suspect…
test-sufficiency
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
fresh-eyes
Clean-context design reviewer. Reviews just-written code changes with zero memory of writing them — catches half-finished changes and cross-file drift (a file updated but the file pointing at it left stale), then over-engineering, scope creep, and simpler alternatives: the judgment calls hooks and checklists cannot…
proof-eyes
Evidence verifier for repo-xray scan results. Opens the actual code at each scanner candidate and decides which ones are real — filtering the noise a regex/AST scan inevitably produces. Use for /hi-vibe:check (spawned by default), or when the user asks 이거 진짜 중복이야?, 스캔 결과 확인해줘, 후보 걸러줘. Not for design opinions or…