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 Eliyce/paqad-ai --skill business-logic-abuse-reviewgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/business-logic-abuse-review)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/business-logic-abuse-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/business-logic-abuse-review/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/eliyce/paqad-ai/business-logic-abuse-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/business-logic-abuse-review.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 | $0.00023 | $0.00572 |
| Opus 5 | $0.00012 | $0.00286 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
business-logic-abuse-review 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.
What it actually says
What It Does
Turns business workflow descriptions into concrete abuse hypotheses so pentest reports can cover replay, bypass, approval skipping, and invalid transitions with project context.
Use This When
Use this when module docs describe stateful workflows, approvals, payments, exports, retries, invites, or any action that can be abused without breaking auth.
Inputs
- Read the workflow and state-related module docs first.
- Read
references/abuse-cases.mdbefore selecting hypotheses. - Read tests and runtime artifacts that could confirm or refute those hypotheses.
Procedure
- Run
scripts/find-workflow-docs.shto enumerate candidate workflow/state docs. - Extract state changes, approvals, and high-value actions from those docs.
- For each, pick an abuse-case tag from
assets/abuse-case-categories.txt(replay, double-submit, invalid-transition, bypass-approval, race, rollback-skip, overspend). - Confirm whether tests or runtime evidence cover that abuse path; record the exact missing proof.
- Format per
assets/output.template.mdand validate withscripts/lint-findings.sh.
Output Contract
- Match
assets/output.template.md:## Findings,### {{module}} — {{abuse-case-tag}}, withModule:,Step:,Abuse case:,Missing proof:,Reproduction:segments. - Output must pass
scripts/lint-findings.sh(exit 0). - Reproduction steps must be concrete enough for a manual retest.
Escalate / Stop Conditions
- Ask when the workflow is clearly high-value but the module docs do not describe its state transitions.
- Warn when the docs suggest irreversible or financial actions without matching abuse-focused test evidence.
- Do not present a generic “business logic risk” without naming the exact abuse case.
Resources
references/abuse-cases.mdscripts/find-workflow-docs.shscripts/lint-findings.shassets/output.template.mdassets/abuse-case-categories.txtagents/openai.yaml
What ships with it
6 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.
- 9d ago First seen · 66 lines · 23 tokens per session scan A bc9bd6c49291
business-logic-abuse-review is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 572 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
auto-go
A command that implements code from a SPEC, a document describing the required behavior and work.
auto-plan
A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.
agent-pipeline
Multi-agent pipeline orchestration skill.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.