AutoSkillit: Skill for Claude Code

.claude/skills/check-bearing/SKILL.md

check-bearing is a skill for Claude Code from TalonT-Org/AutoSkillit. It costs 44 tokens per session (4,312 once invoked), scanned A, original, MIT.

A strategic review workflow for checking whether a branch or pull request supports a project's long-term direction. A pull request is a proposed set of code changes for review before merging.

In plain words
What is it for?
Use it before merging a branch, during pull-request review, after a sprint, or when comparing implementation approaches against a compass document.
Why use it?
It shows whether current changes move toward, drift from, or limit the project's chosen strategic directions before they are merged.

Skill for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: mentions subagents.

This is TalonT-Org/AutoSkillit's own configuration. It tells Claude Code how to work on AutoSkillit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AutoSkillit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TalonT-Org/AutoSkillit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TalonT-Org/AutoSkillit/main/.claude/skills/check-bearing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit

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 check-bearing

README.md
[![agentmods](https://agentmods.dev/badge/skills/talont-org/autoskillit/check-bearing/github.svg)](https://agentmods.dev/skills/talont-org/autoskillit/check-bearing)
Your own site
<a href="https://agentmods.dev/skills/talont-org/autoskillit/check-bearing"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/check-bearing/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 check-bearing

Your own site · 80×15
<a href="https://agentmods.dev/skills/talont-org/autoskillit/check-bearing"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/check-bearing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,312 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 $0.00044 $0.04312
Opus 5 $0.00022 $0.02156
Sonnet 5 $0.00009 $0.00862
Haiku 4.5 $0.00004 $0.00431

Measured 9d ago against content hash be0efd4b5dbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

check-bearing 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 9d 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.

.claude/skills/check-bearing/SKILL.md · 503 lines

How it starts

The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check Bearing — Strategic Alignment Review

When to Use

  • Before merging a branch — verify it does not close off strategic paths
  • During PR review — understand how changes affect long-term options
  • After a sprint — assess cumulative alignment of recent work
  • When evaluating whether to pursue a particular implementation approach
  • As a gate in the implementation or merge-prs recipe

Arguments

/check-bearing {target} compass_path=<path>
  • {target} — Required. One of:

    • A branch name (e.g., feature/add-provenance)
    • A PR number (e.g., #142)
    • A PR URL (e.g., https://github.com/owner/repo/pull/142)
    • HEAD — assess uncommitted + staged changes on the current branch
    • --since <branch> — assess all changes since divergence from that branch
  • compass_path=<path> — Required. Absolute or relative path to a compass document produced by /chart-course. The file must contain a ---compass-data--- ... ---end-compass-data--- block.

Target Resolution

Branch name:

  • Detect base branch via git merge-base against main and develop
  • Use the closer base (fewer commits ahead)
  • Diff: git diff {merge_base}...{branch}

PR number or URL:

  • Extract PR metadata via gh pr view {number} --json baseRefName,title,body,files
  • Diff: gh pr diff {number}

HEAD:

  • Diff: git diff (unstaged) + git diff --cached (staged)

--since :

  • Diff: git diff {branch}...HEAD
  • Log: git log --oneline {branch}...HEAD

Critical Constraints

NEVER:

  • Modify any source code files — this is a read-only analysis skill
  • Create files outside {{AUTOSKILLIT_TEMP}}/check-bearing/
  • Assess implementation quality — that is audit-impl's domain
  • Recommend specific code changes — report alignment facts, not fixes
  • Skip directions because they seem irrelevant — assess ALL directions in the compass
  • Mark a direction as CLOSES without specific architectural evidence showing why the change creates a barrier that would require significant rework to undo
  • Use the compass priority field to suppress findings — all closures matter regardless of priority
  • Conflate "this change doesn't advance direction X" with "this change harms direction X" — most changes are genuinely NEUTRAL to most directions

Read the full file on GitHub · 503 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. 9d ago First seen · 503 lines · 44 tokens per session scan A be0efd4b5dbf

Subscribe to this mod's changes

check-bearing is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 4,312 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.