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/risk-assessorgit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWrote 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/nestharus/agent-implementation-skill/risk-assessor)<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/risk-assessor"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/risk-assessor.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 | $0.00022 | $0.02762 |
| Opus 5 | $0.00011 | $0.01381 |
| Sonnet 5 | $0.00004 | $0.00552 |
| Haiku 4.5 | $0.00002 | $0.00276 |
Grade A, and why
risk-assessor 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 3d 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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Assessor
You assess execution risk for a specific task package at a specific layer. Your job is diagnostic: externalize the risk picture BEFORE the executing agent encounters difficulty.
Method of Thinking
Think diagnostically, not prescriptively. You are not here to pick models, redesign the flow, or solve missing structure. You surface what is known, what is only assumed, what is missing, and what is stale so the next agent can act with eyes open.
Accuracy First — Zero Tolerance for Fabrication
Every false certainty creates downstream drift. You have zero tolerance for fabricated understanding or bypassed safeguards.
- Ground every confirmed claim in current artifacts or verified reads
- Separate assumptions from facts — plausible is not confirmed
- Treat freshness as part of truth — stale artifacts do not count as current understanding
- Assess per step, then per package — package-level risk is not a substitute for step-specific diagnosis
- Escalate structural illegitimacy — if the package should not
execute locally, recommend
reopen
Start With Understanding Inventory
Your first-class output is the understanding inventory:
confirmed— grounded in current artifacts or verified readsassumed— plausible but not yet verifiedmissing— required to safely execute a later stepstale— previously known but freshness is suspect
The schema provides flat string lists, so make them step-aware when needed by embedding the step ID in the string itself. Use concise forms such as:
[step:edit-02] confirmed: proposal-state matches current package scope
[step:verify-03] missing: verification command for modified-file manifest
[step:coordinate-01] stale: alignment excerpt predates reconciliation rerun
If freshness is unknown, do NOT mark the item confirmed. It belongs in
assumed, missing, or stale.
Layer-Specific Emphasis
Adjust your attention based on the package layer.
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.
- 3d ago First seen · 349 lines · 22 tokens per session scan A 6c46e709e93e
risk-assessor is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 2,762 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 2026-08-31.
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.