capture-guidance

capture-guidance is a skill for Claude Code from leifericf/agentic-sdk. It costs 30 tokens per session (834 once invoked), scanned A, original, MIT.

A procedure for recording corrections about work or process, and preferences about how an agent should interact with you.

In plain words
What is it for?
Use it to save rules, style corrections, interaction preferences, and other session guidance for later reuse.
Why use it?
It prevents useful feedback from being lost and sends each kind of guidance to the appropriate project or profile location.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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 skills/leifericf/agentic-sdk/capture-guidance
Any agent
npx skills add leifericf/agentic-sdk --skill capture-guidance
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code.

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 capture-guidance

README.md
[![agentmods](https://agentmods.dev/badge/skills/leifericf/agentic-sdk/capture-guidance.svg)](https://agentmods.dev/skills/leifericf/agentic-sdk/capture-guidance)
Your own site
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/capture-guidance"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/capture-guidance.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 834 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 5.1 $0.00030 $0.00834
Opus 5 $0.00015 $0.00417
Sonnet 5 $0.00006 $0.00167
Haiku 4.5 $0.00003 $0.00083

Measured 6d ago against content hash 958de0d260f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

capture-guidance 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 6d 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/capture-guidance/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

capture-guidance

One capture primitive, two routes: a correction goes to the guidance inbox for later promotion; an interaction preference goes to the profile every session reads.

Procedure

  1. Classify the input.

    • A correction or ruling about the work or the process ("don't do X", "always Y here", "that pattern is banned"): route to the inbox.
    • An interaction preference (verbosity, clarifying questions per turn, ask-first versus decide-and-continue, probing depth, output style, hard red lines): route to the profile.
  2. Correction route. Append one entry to ~/.agentic-sdk/<project>/guidance/inbox.edn (a vector; [] if missing; gitignored working state, consumed when incorporate-feedback promotes the entry):

    {:date "YYYY-MM-DD"
     :rule "one imperative sentence, the way a reviewer would state it"
     :context "what happened that triggered the correction"
     :applies-to :clojure | :zig | :c | :elixir | :native-edge | :persistence | :ui | :tests | :tooling | :process
     :suggested-home "check-style/references/<lang>-style.md"}
    

    :applies-to reflects the project's surfaces: the four languages; :native-edge for any C ABI, NIF, or foreign-function boundary; :persistence for the shell's store and transactions; :ui for the UI; :tests for the suite; :tooling for build, deps, or release; :process for anything cross-cutting. :suggested-home is your best guess: a reference file, a check-* or write-* skill body, a future ADR, or a lint rule when the rule is mechanically checkable. If the correction contradicts an existing rule, set :conflicts-with "<file>"; incorporate-feedback resolves it with the maintainer.

  3. Preference route. Upsert the preference into ~/.agentic-sdk/<project>/guidance/profile.edn (a map; {} if missing; gitignored). One key per preference, plain values:

    {:verbosity :concise                       ; :concise | :balanced | :detailed
     :questions-per-turn 2
     :default-behavior :decide-and-continue    ; :ask-first | :decide-and-continue | :decide-silently
     :probing-depth :standard                  ; :light | :standard | :deep
     :output-style :structured                 ; :structured | :prose | :mix
     :red-lines ["never advance main autonomously"]}
    

Read the full file on GitHub · 79 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. 6d ago First seen · 79 lines · 30 tokens per session scan A 958de0d260f0

Subscribe to this mod's changes

capture-guidance is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 834 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens