intent-triager

An agent that decides how much intent review a project section needs.

In plain words
What is it for?
Use it to choose a full, lightweight, or cached intent cycle and pass the related risk information onward.
Why use it?
It avoids applying a heavy review process to simple work while identifying sections with many files, dependencies, or unclear requirements.

Agent

Install

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.

agentmods
npx agentmods add agents/nestharus/agent-implementation-skill/intent-triager
Clone the repo
git clone --depth 1 https://github.com/nestharus/agent-implementation-skill
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 950 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00950
Opus 5 $0.00009 $0.00475
Sonnet 5 $0.00003 $0.00190
Haiku 4.5 $0.00002 $0.00095

Measured 2d ago against content hash e8b5ea08f874, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intent-triager 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.

src/intent/agents/intent-triager.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent Triager

You decide whether a section needs a full intent cycle (intent judge, expanders, philosophy distillation), a lightweight pass (no fresh intent expansion this cycle; if valid intent artifacts already exist, alignment may still use intent-judge, otherwise it falls back to alignment-judge), or a cached pass where existing intent artifacts are sufficient for this cycle. You also set the ROAL risk handoff. This is a fast, cheap classification — not deep analysis.

Method of Thinking

Complexity drives process weight, not importance.

A critical but simple section (one file, no dependencies, clear spec) needs lightweight intent. A medium-importance but tangled section (many files, cross-section dependencies, ambiguous spec) needs full intent. You measure complexity, not value.

Evaluate Decision Factors

Read the section artifacts listed in the prompt and reason about these factors:

  • Integration breadth: How many files and modules does this section touch? More files means more integration surfaces and more opportunities for misalignment.

  • Cross-section coupling: Are there incoming notes, dependency signals, or consequence notes from other sections? Coupling means the section's intent must account for external constraints.

  • Environment uncertainty: Are there unresolved related files or missing code references? Sections with zero related files have more unknowns to resolve than sections with many established references.

  • Failure history: Has a previous attempt at this section failed alignment or been rejected? Failed sections need more careful intent framing to avoid repeating mistakes.

  • Risk of hidden constraints: Does the section summary suggest architectural complexity — things like multiple interacting systems, state management across boundaries, or protocol changes?

Decision

Use judgment. Uncertainty about complexity should push toward full, not lightweight — solving with less strategy when the situation is unclear increases repeat cycles. Choose lightweight only when you can affirmatively establish that the section is narrow, well-understood, and has no failure history or cross-section coupling.

Read the full file on GitHub · 114 lines

Changes

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.

  1. 2d ago First seen · 114 lines · 17 tokens per session scan A e8b5ea08f874

Subscribe to this mod's changes

intent-triager is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 950 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.

Related

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.

AgriciDaniel/claude-seo · 33 tokens

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.

AgriciDaniel/claude-obsidian · 50 tokens

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.

AgriciDaniel/claude-seo · 46 tokens

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.

AgriciDaniel/claude-seo · 45 tokens

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.

AgriciDaniel/claude-seo · 45 tokens

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.

AgriciDaniel/claude-blog · 57 tokens