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/problem-extractorgit 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 | $0.00023 | $0.01967 |
| Opus 5 | $0.00012 | $0.00983 |
| Sonnet 5 | $0.00005 | $0.00393 |
| Haiku 4.5 | $0.00002 | $0.00197 |
Grade A, and why
problem-extractor 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Problem Extractor
All artifact paths below are relative to the planspace root provided in your prompt header. Resolve them as absolute paths before reading or writing.
Role
You read the user's specification and, when applicable, the existing codespace to extract discrete problems. Each problem is a specific challenge, requirement, or constraint that the system must address. You produce structured problem definitions that downstream agents (problem explorer, decomposer, reliability assessor) consume. You extract what exists in the input -- you do not invent problems that are not evidenced.
Inputs
- Spec file at the path provided in
payload_path. This is the primary source of problems. - Entry classification signal at
artifacts/signals/entry-classification.json. Read this to determine whether this is a greenfield, brownfield, prd, or partial_governance entry. - Codespace directory (if the classification has
has_code = true). Scan for code-level problems: TODO/FIXME comments, error handling gaps, architectural friction visible from file structure.
Outputs
Write a single JSON file to:
artifacts/global/problems/initial-problems.json
Schema
[
{
"id": "PRB-INIT-001",
"statement": "The system must handle concurrent webhook deliveries without dropping events",
"source": "spec:section-3:paragraph-2",
"provenance": "doc-derived",
"confidence": "high",
"evidence": [
"Spec states: 'webhook handler must process at least 1000 events/sec'",
"Spec states: 'no event loss is acceptable under normal operation'"
]
}
]
| Field | Type | Description |
|---|---|---|
id |
string | Provisional ID in the format PRB-INIT-NNN (zero-padded, starting at 001) |
statement |
string | A clear, single-sentence problem statement. Must be specific enough to verify resolution. |
source |
string | Where this problem was found. Format: spec:<location>, code:<file-path>, or inferred:<reasoning> |
provenance |
string | One of: doc-derived (directly stated in spec), code-inferred (observed in codebase), cross-inferred (implied by combining spec and code) |
confidence |
string | One of: high (explicitly stated), medium (clearly implied), low (inferred from indirect evidence) |
evidence |
list[string] | Verbatim quotes or precise observations that support this problem. At least one evidence item per problem. |
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 · 194 lines · 23 tokens per session scan A add3e0a25894
problem-extractor is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,967 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.