guide-alignment

guide-alignment is a skill for Claude Code, Codex from c9r-io/orchestrator. It costs 82 tokens per session (873 once invoked), scanned A, original, MIT.

A repair procedure for keeping command-line documentation aligned with the commands the program actually provides. CLI means a text-based interface where users run commands and options.

In plain words
What is it for?
Use it after CLI changes or documentation-parity failures to update generated command data, English and Chinese guides, the built-in guide, and related tests.
Why use it?
It finds documentation drift—when guides describe commands or flags that no longer match the software—and helps restore passing checks.

Skill for Claude CodeCodex

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/c9r-io/orchestrator/guide-alignment
Any agent
npx skills add c9r-io/orchestrator --skill guide-alignment
Clone the repo
git clone --depth 1 https://github.com/c9r-io/orchestrator

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 guide-alignment

README.md
[![agentmods](https://agentmods.dev/badge/skills/c9r-io/orchestrator/guide-alignment.svg)](https://agentmods.dev/skills/c9r-io/orchestrator/guide-alignment)
Your own site
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/guide-alignment"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/guide-alignment.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 873 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 $0.00082 $0.00873
Opus 5 $0.00041 $0.00436
Sonnet 5 $0.00016 $0.00175
Haiku 4.5 $0.00008 $0.00087

Measured 5d ago against content hash a66ebc3ea301, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guide-alignment 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 5d 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/guide-alignment/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guide Alignment

Since FR-154, CLI-vs-documentation drift is detected mechanically — this skill is the repair procedure, not the detector. The single source of truth is the clap tree, projected into config/governance/cli-surface.json; three surfaces are held to it in CI:

Surface Enforced by Where it runs
config/governance/cli-surface.json freshness cli_surface_json_is_fresh (cargo test) test job
built-in guide (crates/cli/src/commands/guide.rs) guide_matches_clap_leaves (cargo test) + gate check 5 test + governance jobs
docs/guide/07-cli-reference.md EN + ZH scripts/qa/test-cli-doc-parity.sh (ci-required) governance job

Procedure

  1. Regenerate the surface after any crates/cli/src/cli.rs change:

    ORCHESTRATOR_WRITE_CLI_SURFACE=1 cargo test -p orchestrator-cli cli_surface_json_is_fresh
    

    Read the diff of config/governance/cli-surface.json — it names exactly what changed (new paths, flags, defaults, hidden markers).

  2. Run the detector and read its diagnostics — never re-derive the drift by hand:

    bash scripts/qa/test-cli-doc-parity.sh
    cargo test -p orchestrator-cli guide_matches_clap_leaves
    

    The gate prints the missing paths per document, invalid/hidden invocations, and the two-sided guide-vs-surface diff.

  3. Fix the built-in guide first: add/remove GuideEntry items in crates/cli/src/commands/guide.rs (command_entries(); pseudo-topics live separately in topic_entries()). Summaries come from the about strings in cli-surface.json; examples must use real flags with real defaults.

  4. Fix the markdown references: docs/guide/07-cli-reference.md, then its structural mirror docs/guide/zh/07-cli-reference.md. Coverage counts an inline backtick span or a fenced-code-block line that starts with the command path; HTML-commented mentions do not count. Follow the existing section layout; flags in tables, examples in ```bash blocks.

Read the full file on GitHub · 73 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. 5d ago First seen · 73 lines · 82 tokens per session scan A a66ebc3ea301

Subscribe to this mod's changes

guide-alignment is a skill published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 873 once invoked, about $0.0004 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 2026-08-30.