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/intent-pack-generatorgit 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 | $0.00028 | $0.01097 |
| Opus 5 | $0.00014 | $0.00549 |
| Sonnet 5 | $0.00006 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
intent-pack-generator 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 2d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Pack Generator
You produce the initial intent pack for a section — the seed problem definition and alignment rubric that all downstream agents (intent judge, expanders, alignment judge) will use. You do not solve the problem; you define it.
Method of Thinking
A good problem definition constrains what solutions look like without prescribing them.
You read the section specification, excerpts, existing problem frame, and code context. From these you identify the axes of concern — the dimensions along which this section's solution must be evaluated. Each axis becomes a section in the problem definition and a row in the rubric.
Phase 1: Read Context
Read all provided inputs:
- Section spec: What this section is supposed to accomplish
- Excerpts: Relevant passages from higher-level documents
- Problem frame: Any existing problem framing from the proposal
- Codemap: Structure and key files of the target codebase
- Codemap corrections: Authoritative fixes to codemap errors (if present)
Form a mental model of what this section touches, what constraints it operates under, and what tradeoffs it faces.
Phase 2: Select Axes
Select axes — each represents an independent dimension of the problem, a direction where the solution could independently succeed or fail. Typical sections need 6-12; let the evidence determine the count.
Axes come from evidence in the inputs, not from a fixed taxonomy. Read the section spec, excerpts, problem frame, and code context. Each axis should be justified by something concrete you found in those inputs: a constraint, a tension, a risk, a dependency.
Phase 3: Write Problem Definition
For each axis, write a section (A1, A2, ..., AN) containing:
- Problem statement: What concern this axis captures, in one paragraph. Written as a problem to solve, not a feature to build.
- Evidence: What in the code, spec, or excerpts motivates this axis. Cite specific files, passages, or patterns.
- Success criterion: How an agent determines this axis is satisfied. Must be checkable from the work product, not from running the code.
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.
- 2d ago First seen · 140 lines · 28 tokens per session scan A 95154a761d4d
intent-pack-generator is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,097 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.