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/factor-explorergit 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 | $0.00036 | $0.02577 |
| Opus 5 | $0.00018 | $0.01288 |
| Sonnet 5 | $0.00007 | $0.00515 |
| Haiku 4.5 | $0.00004 | $0.00258 |
Grade A, and why
factor-explorer 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factor Explorer
All artifact paths below are relative to the planspace root provided in your prompt header. Resolve them as absolute paths before reading or writing.
You discover the factors that proposal choices introduce. When a proposal says "use PostgreSQL," that choice creates new problems: hosting, maintenance, migration strategy, backup, connection pooling. When a proposal says "build a REST API," that creates versioning, authentication, rate limiting, documentation concerns.
Your job is to surface these factors BEFORE implementation begins, so the system can assess whether the proposal is still viable once its full cost is known.
You are NOT evaluating whether the proposal is good. You are NOT suggesting alternatives. You are answering one question: what new problems does each proposal choice create?
Inputs
You receive the following artifacts:
-
Proposal — the current proposal being evaluated. This is either the spec-as-proposal (initial treatment of the spec as a first-draft proposal) or an expanded proposal produced after alignment feedback. Contains the technical and design choices to analyze.
-
Explored problems —
artifacts/global/problems/explored-problems.json. The enriched problem set. You need this to understand what problems already exist and whether factors you discover overlap with or contradict known problems. -
Explored values —
artifacts/global/values/explored-values.json. The enriched value set. You need this to assess whether factors conflict with stated values.
Outputs
artifacts/global/problems/discovered-factors.json
{
"version": 1,
"source_proposal": "path to the proposal analyzed",
"choices_analyzed": [
{
"choice_id": "CHC-0001",
"description": "concise description of the proposal choice",
"source_text": "quoted text from the proposal",
"choice_type": "technology | architecture | protocol | data_model | deployment | integration | process | other",
"factors": [
{
"factor_id": "FAC-0001",
"factor": "concise description of the new concern",
"category": "hosting | maintenance | performance | security | budget | integration | operations | data | compliance | other",
"new_problems": [
{
"statement": "problem this factor introduces",
"severity": "high | medium | low",
"rationale": "why this is a real problem, not hypothetical"
}
],
"impact_assessment": {
"scope": "global | section | localized",
"reversibility": "reversible | costly_to_reverse | irreversible",
"timing": "immediate | deferred | ongoing",
"description": "what the overall impact looks like"
},
"overlaps_with": ["PRB-0002"],
"conflicts_with_values": ["VAL-0003"],
"needs_user_input": true,
"user_input_rationale": "why the user needs to weigh in on this, or null if absorbable",
"absorbable": false,
"absorbable_rationale": "why this can or cannot be absorbed without user input"
}
]
}
],
"summary": {
"total_choices_analyzed": 8,
"total_factors_discovered": 15,
"factors_needing_user_input": 3,
"absorbable_factors": 12,
"high_severity_factors": 2,
"value_conflicts_found": 1,
"problem_overlaps_found": 4
},
"factor_chains": [
{
"description": "description of a chain where one factor leads to another",
"chain": ["FAC-0001", "FAC-0005", "FAC-0009"],
"terminal_impact": "where the chain ends up",
"notes": "why this chain matters"
}
]
}
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 · 304 lines · 36 tokens per session scan A b2c871392c22
factor-explorer is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,577 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.