asa-anchor-composition-planner

asa-anchor-composition-planner is a skill for Claude Code, Codex from 3yesore/LetUenforskills. It costs 27 tokens per session (840 once invoked), scanned A, original, MIT.

An internal guide for combining reusable parts of skills into a temporary composition, prompt change, note, or workflow insert. It helps choose the smallest useful form instead of creating a full new workflow.

In plain words
What is it for?
Use it when deciding which extracted skill instructions to reuse, how to combine them, and whether the result should be temporary or saved.
Why use it?
It prevents unnecessary skill-building and rejects pieces that lack required dependencies or conflict with existing skills.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when deciding which extracted skill instructions to reuse, how to combine them, and whether the result should be temporary or saved.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/3yesore/letuenforskills/asa-anchor-composition-planner
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.

Any agent
npx skills add 3yesore/LetUenforskills --skill asa-anchor-composition-planner
Clone the repo
git clone --depth 1 https://github.com/3yesore/LetUenforskills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for asa-anchor-composition-planner

README.md
[![agentmods](https://agentmods.dev/badge/skills/3yesore/letuenforskills/asa-anchor-composition-planner/github.svg)](https://agentmods.dev/skills/3yesore/letuenforskills/asa-anchor-composition-planner)
Your own site
<a href="https://agentmods.dev/skills/3yesore/letuenforskills/asa-anchor-composition-planner"><img src="https://agentmods.dev/badge/skills/3yesore/letuenforskills/asa-anchor-composition-planner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for asa-anchor-composition-planner

Your own site · 80×15
<a href="https://agentmods.dev/skills/3yesore/letuenforskills/asa-anchor-composition-planner"><img src="https://agentmods.dev/badge/skills/3yesore/letuenforskills/asa-anchor-composition-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 840 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00027 $0.00840
Opus 5 $0.00014 $0.00420
Sonnet 5 $0.00005 $0.00168
Haiku 4.5 $0.00003 $0.00084

Measured 11d ago against content hash b04c7ce5c890, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

asa-anchor-composition-planner 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 11d 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.

skills/asa-anchor-composition-planner/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ASA Anchor Composition Planner

Use this internal meta-skill when LetUen has extracted anchors and must decide how to combine them for a user goal without forcing workflow solidification.

This skill fixes the failure mode where every useful skill fragment is turned into a heavy new workflow or new skill even when the user only wants a temporary composition, prompt patch, rule patch, learning note, or partial workflow insert.

Inputs

  • Minimal Anchor Cards or normalized anchors.
  • User composition goal and preferred reuse form.
  • Existing user skill snapshot when available.
  • Trigger overlap and resource conflict notes when available.
  • Evidence and risk scores from reviewer/auditor stages.
  • Target agent or host project constraints.

Process

  1. Identify the user's requested reuse form before selecting anchors.
  2. Prefer the lightest useful output: reference_only, temporary_composition, prompt_patch, or learning_note unless the user asks for persistence.
  3. Select anchors whose reuse_modes match the requested form.
  4. Reject anchors with missing hard dependencies unless an adapter is explicitly available.
  5. Detect trigger overlap with existing user skills and choose a dispatch policy.
  6. Keep existing user skills primary by default when overlap is ambiguous.
  7. Produce a non-destructive plan that can be reviewed before any file changes.
  8. Escalate to workflow or new skill output only when explicitly requested.

Output Contract

Return a planner-only composition plan suitable for composition_plan.json:

schema_version: 1
composition_form: reference_only | temporary_composition | prompt_patch | agent_rule_patch | workflow_insert | tool_adapter | template_pack | quality_gate | learning_note | full_workflow_blueprint | new_skill_spec
summary:
  zh:
  en:
selected_anchors:
  - anchor_id:
    reason:
    selected_reuse_mode:
rejected_anchors:
  - anchor_id:
    reason:
conflicts:
  - conflict_type: trigger_overlap | resource_missing | output_mismatch | runtime_assumption | none
    description:
    resolution:
dispatch_policy:
  mode: prefer_existing_skill | prefer_letuen_composition | ask_user | route_by_anchor_type | run_both_then_compare | disabled
  reason:
outputs:
  - kind: prompt_patch | agent_rule_patch | workflow_insert | tool_adapter | template_pack | quality_gate | learning_note | full_workflow_blueprint | new_skill_spec
    path:
    destructive: false
    reversible: true
solidification:
  requested: false
  reason:
next_steps: []

Read the full file on GitHub · 103 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. 11d ago First seen · 103 lines · 27 tokens per session scan A b04c7ce5c890

Subscribe to this mod's changes

asa-anchor-composition-planner is a skill published in the GitHub repository 3yesore/LetUenforskills (2 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 840 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 skills, from other repositories

link-memory

Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.

gowtham0992/link · 0 tokens

link-retrieve

Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.

gowtham0992/link · 42 tokens

link-health

Use at the start of Link work when readiness is unclear, after installs or upgrades, and before repairs; verify health, inspect interrupted writes, back up, and repair generated indexes without MCP.

gowtham0992/link · 41 tokens

link-ingest

Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.

gowtham0992/link · 44 tokens

kb

Use when compiling raw sources into the wiki, querying the knowledge base, running health checks or lint on the wiki, evolving or improving wiki coverage, or when user says 'compile', 'update the wiki', 'query', 'lint', 'health check', 'evolve', 'what's missing', or 'suggest improvements'. Also triggers on questions…

rvk7895/llm-knowledge-bases · 80 tokens

kb-init

Use when setting up a new knowledge base, bootstrapping an Obsidian vault, or when user says 'init kb', 'new knowledge base', 'create kb', or 'setup vault'. Triggers on any request to initialize or scaffold a knowledge base project.

rvk7895/llm-knowledge-bases · 57 tokens