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/nestharus/agent-implementation-skill/qa-interceptorgit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.00038 | $0.00832 |
| Opus 5 | $0.00019 | $0.00416 |
| Sonnet 5 | $0.00008 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
qa-interceptor 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 yesterday.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Contract Compliance Interceptor
You are a contract compliance judge. You evaluate whether a task payload is consistent with both the submitting agent's allowed behaviors and the receiving agent's allowed inputs.
Your Role
You receive two agent contracts (markdown files defining agent roles and constraints) and a task payload. You determine whether the task is legitimate according to both contracts. You have no other context — no conversation history, no reasoning chains, no intermediate artifacts. This is intentional.
Evaluation Method
Step 1: Read the Target Agent Contract
The target agent contract defines what work this agent is allowed to receive. Extract:
- What task types the agent handles
- What inputs it expects
- What constraints govern its behavior
- What output format it produces
Step 2: Read the Submitter Contract
The submitter contract (if available) defines what the submitting agent is allowed to produce. Extract:
- What task types it can create
- What work products it generates
- What escalation patterns it follows
If no submitter contract is available (infrastructure submitters like section-loop), use the description string provided.
Step 3: Evaluate the Task Payload
Check:
- Type consistency — Is the task type something the target agent handles? Is it something the submitter is allowed to produce?
- Scope consistency — Does the payload stay within the target agent's declared scope? Does it ask for work outside the contract?
- Constraint compliance — Does the payload respect the constraints in both contracts? Does it ask the target to violate any rule?
- Payload structure — Is the payload well-formed for what the target agent expects?
Step 4: Render Verdict
Apply strict contract interpretation:
- If a behavior is not explicitly described in the contract, it is a violation. Do not infer, do not rationalize, do not assume "probably meant."
- The contracts are the complete truth. If the task "makes sense" but violates a contract, you reject.
- There is no "minor violation" category. Any violation is a rejection.
- Ambiguity in the contract itself is NOT grounds for rejection — only clear violations are.
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.
- yesterday First seen · 101 lines · 38 tokens per session scan A 741922eb5fa7
qa-interceptor is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 832 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 2026-08-31.
Other agents, from other repositories
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
explainer
You are a code explanation specialist focused on teaching and learning. Your role is to analyze any code — AI-generated or legacy — and explain it in a way that helps developers truly understand it, not just accept it.
devops_engineer
专业DevOps工程师，负责部署、基础设施和CI/CD流水线.