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 alivirgo/Major-AI-Skills --skill agent-tool-replay-testgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/agent-tool-replay-test)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/agent-tool-replay-test"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/agent-tool-replay-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/alivirgo/major-ai-skills/agent-tool-replay-test"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/agent-tool-replay-test.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 | $0.00041 | $0.00886 |
| Opus 5.5 | $0.00016 | $0.00354 |
| Sonnet 5.5 | $0.00008 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
agent-tool-replay-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 21d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Tool Replay Test AI Skill Guide (Claude)
Overview & Engine Architecture
Live agents are expensive and flaky. Record/replay at the SDK or tool boundary gives deterministic CI: assert validation, error handling, and “must not call” policies without paying for tokens. Replay does not prove the model still chooses the right tools—that needs live/eval gates (@prompt-regression-gate).
Claude operates as a Principal Agent Test Architect for cassettes, contract assertions, clock/ID freezing, and unknown-outcome handling after timeouts.
┌─────────────────────────────────────────────────────────────┐
│ RECORD (once): LLM decisions ± tool results → cassette │
│ REPLAY (CI): inject recordings; optionally run real tools │
│ ASSERT: schemas, sequences, deny-lists, idempotency │
└─────────────────────────────────────────────────────────────┘
Scope
- Read tool contracts: read-only vs mutating.
- Use project test runner + mocks; no production networks in
replaymode. - Sanitize cassettes (no credentials)—
@ai-pii-redaction-review. - Label coverage: replay contract ≠ e2e model behavior.
Fixture matrix (minimum)
| Case | Expect |
|---|---|
| Success | Valid args → OK result |
| Timeout | Bounded retry policy; unknown outcome path |
| Permission denied | No side effect; surfaced error |
| Malformed tool JSON | Reject via @llm-json-contract-check |
| Partial failure | Compensating / reconcile logic |
| Unknown fields / bad IDs | Validation reject before dispatch |
| Mutating call | AuthZ + idempotency key before effect |
| Policy deny | Tool absent from allow-list never invoked |
Determinism rules
- Freeze clocks/randomness; stable paths in prompts (no
uuid4()in recorded args). - Modes:
record|replay(CI; miss = fail, no network) |passthrough. - Prefer SDK-boundary recorders (OpenAI/Anthropic patch) over brittle raw HTTP VCR for agents.
- Two styles: (A) stub tool results entirely; (B) replay LLM decisions but execute tools against safe stubs—pick explicitly.
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.
- 21d ago Changed · +59 lines · +14 tokens per session 6f5bd05854fd
- 1mo ago First seen · 35 lines · 27 tokens per session scan A 475c1afbe00f
agent-tool-replay-test is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 886 once invoked, about $0.0002 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 2026-09-12.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
api-contract-testing
Design and review API contract tests across providers and consumers. Use for schema changes, compatibility regressions and client integration failures.
advanced-evaluation
Design LLM-as-judge rubrics, direct scores and pairwise comparisons. Use for judge models, evals, position bias and calibration against human labels.
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
api-fuzzing-bug-bounty
Provide comprehensive techniques for testing REST, SOAP, and GraphQL APIs during bug bounty hunting and penetration testing engagements. Covers vulnerability discovery, authentication bypass, IDOR exploitation, and API-specific attack vectors.
appium-skill
Generates production-grade Appium mobile automation scripts for Android and iOS in Java, Python, or JavaScript. Supports real device and emulator testing locally and on TestMu AI cloud with 100+ real devices.