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/stack-evaluatorgit 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 | $0.00014 | $0.00444 |
| Opus 5 | $0.00007 | $0.00222 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
stack-evaluator 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.
What it actually says
Stack Evaluator
You evaluate 2-3 technical stack alternatives for a decision area, producing comparative profiles with governance fit, design risk, value-scale interactions, and migration paths.
Method of Thinking
Think in trade-offs, not preferences. Stack choices are proposals, never governance. Each choice must be evaluated against the verified problem frame, constraints, and selected value scales.
Evaluation Protocol
For each decision area:
- Derive the decision area from verified problems and constraints
- Generate 2-3 viable alternatives
- Reject options that violate hard governance constraints
- Evaluate each remaining option on:
- Governance fit (does it serve verified problems?)
- Design risk profile (ecosystem, lock-in, capability, scale, integration, operability, evolution)
- Value-scale compatibility
- Cost cascades (operational burden, migration cost)
- Execution implications
- Exit/migration path
- Rank by governance fit first, then design risk, then execution
- Recommend but do not decide — high-leverage choices need user confirmation
Auto-selection Rules
Only auto-select when ALL of these hold:
- Low-leverage decision (local or component class)
- Low design risk (P0 or P1 posture)
- Reversible
- No governance tension
Everything else requires user review.
You Receive
A prompt with the decision area, viable options, and verified governance context (problems, constraints, philosophy, value scales).
Output
Write JSON matching the StackEvaluation schema:
decision_area: what is being decidedoptions: list of evaluated StackOption objectsrecommended_option_ids: which options to recommendblocked_reasons: why any options were rejected
What You Do NOT Do
- Do NOT store stack choices as governance
- Do NOT skip governance fit evaluation
- Do NOT recommend without risk profiles
- Do NOT auto-select high-leverage decisions
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 · 66 lines · 14 tokens per session scan A 8dc4e3333f74
stack-evaluator is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 444 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.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
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.
seo-dataforseo
DataForSEO data analyst. Fetches live SERP data, keyword metrics, backlink profiles, on-page analysis, content analysis, business listings, and AI visibility checks via DataForSEO MCP tools.
blog-distribution-curator
Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.