Borrowing it
Nothing to install: this file belongs to sanmak/specops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sanmak/specops/main/.claude/commands/docs-sync.mdgit clone --depth 1 https://github.com/sanmak/specopsWrote 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.
[](https://agentmods.dev/commands/sanmak/specops/docs-sync)<a href="https://agentmods.dev/commands/sanmak/specops/docs-sync"><img src="https://agentmods.dev/badge/commands/sanmak/specops/docs-sync/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.
<a href="https://agentmods.dev/commands/sanmak/specops/docs-sync"><img src="https://agentmods.dev/badge/commands/sanmak/specops/docs-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02636 |
| Opus 5.5 | $0.00000 | $0.01054 |
| Sonnet 5.5 | $0.00000 | $0.00527 |
| Haiku 4.5 | $0.00000 | $0.00264 |
Grade A, and why
docs-sync 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check for stale documentation after code changes and propose updates for approval.
Instructions
Follow these steps precisely. This command detects documentation that has fallen out of sync with the codebase and proposes targeted fixes.
Step 1: Determine change scope
Identify what has changed in the codebase. Use $ARGUMENTS if provided as a custom git range (e.g., HEAD~3..HEAD or a branch name). Otherwise, default to the last commit plus any uncommitted changes.
# Last commit changes
git diff --name-only HEAD~1..HEAD
# Uncommitted changes (staged + unstaged)
git diff --name-only HEAD
# Detect renames and deletions specifically
git diff --diff-filter=RD --name-only HEAD~1..HEAD
Combine all results into a single deduplicated list of changed files.
Step 2: Match against dependency map
For each changed file, check which documentation may be affected using this mapping:
| Source files changed | Docs to check |
|---|---|
.claude/commands/*.md |
CLAUDE.md (Custom Slash Commands table), docs/COMMANDS.md |
schema.json |
docs/REFERENCE.md (config options), README.md (Configuration section), example configs examples/*.json |
spec-schema.json, index-schema.json |
docs/REFERENCE.md (spec structure), example specs examples/specs/ |
core/workflow.md |
README.md (How It Works), docs/REFERENCE.md (Workflow Phases), CLAUDE.md (Architecture) |
core/review-workflow.md |
docs/TEAM_GUIDE.md, README.md (Team Review Workflow) |
core/safety.md |
CLAUDE.md (Security-Sensitive Files), SECURITY.md |
core/verticals.md |
README.md (Vertical Adaptation), docs/REFERENCE.md |
core/interview.md |
docs/COMMANDS.md (Interview Mode) |
core/init.md |
QUICKSTART.md, docs/COMMANDS.md |
platforms/*/platform.json |
README.md (Platforms table), docs/STRUCTURE.md, CLAUDE.md (Platform Capabilities) |
New platform directory under platforms/ |
README.md, CLAUDE.md (Adding a New Platform), docs/STRUCTURE.md, CONTRIBUTING.md |
generator/generate.py, generator/validate.py |
CLAUDE.md (Key Commands, Validation), docs/STRUCTURE.md |
scripts/*.sh |
CLAUDE.md (Key Commands), QUICKSTART.md |
hooks/* |
CLAUDE.md (Security-Sensitive Files) |
core/templates/*.md |
docs/REFERENCE.md (Spec Templates), example specs |
setup.sh, scripts/remote-install.sh |
QUICKSTART.md (Installation), README.md (Quick Start) |
.github/workflows/*.yml |
CLAUDE.md (CI Notes), CONTRIBUTING.md |
core/config-handling.md |
docs/REFERENCE.md (Configuration Options) |
core/custom-templates.md |
docs/REFERENCE.md (Spec Templates) |
core/data-handling.md |
CLAUDE.md (Security-Sensitive Files) |
core/dependency-safety.md |
CLAUDE.md (Security-Sensitive Files, core modules list), docs/REFERENCE.md (Configuration Options), docs/STRUCTURE.md |
core/dependency-introduction.md |
CLAUDE.md (core modules list), docs/STRUCTURE.md |
core/evaluation.md |
CLAUDE.md (core modules list), docs/REFERENCE.md (Configuration Options), docs/STRUCTURE.md |
core/learnings.md |
CLAUDE.md (core modules list), docs/REFERENCE.md (Configuration Options), docs/STRUCTURE.md, docs/COMMANDS.md (Learn) |
core/error-handling.md |
docs/REFERENCE.md |
core/feedback.md |
docs/COMMANDS.md (Send Feedback) |
core/from-plan.md |
docs/COMMANDS.md (From Plan) |
core/memory.md |
docs/COMMANDS.md (Local Memory), docs/REFERENCE.md |
core/metrics.md |
docs/REFERENCE.md (Usage Metrics), docs/TOKEN-USAGE.md |
core/run-logging.md |
docs/REFERENCE.md (Configuration Options) |
core/plan-validation.md |
docs/REFERENCE.md (Configuration Options) |
core/git-checkpointing.md |
docs/REFERENCE.md (Configuration Options) |
core/pipeline.md |
docs/COMMANDS.md (Pipeline Mode), docs/REFERENCE.md |
core/reconciliation.md |
docs/COMMANDS.md (Drift Detection) |
core/repo-map.md |
docs/COMMANDS.md (Repo Map), docs/REFERENCE.md |
core/simplicity.md |
CLAUDE.md (Simplicity Principle) |
core/steering.md |
docs/COMMANDS.md (Steering Files), docs/STEERING_GUIDE.md |
core/task-delegation.md |
docs/REFERENCE.md (Configuration Options) |
core/task-tracking.md |
docs/REFERENCE.md |
core/tool-abstraction.md |
CLAUDE.md (Tool Abstraction) |
core/writing-quality.md |
CLAUDE.md, README.md (Writing and Engineering Philosophy) |
core/engineering-discipline.md |
CLAUDE.md, README.md (Writing and Engineering Philosophy), docs/STRUCTURE.md |
core/update.md |
docs/COMMANDS.md (Update) |
core/view.md |
docs/COMMANDS.md (View/List) |
core/decomposition.md |
docs/COMMANDS.md (Initiative Management), docs/REFERENCE.md (Spec Structure), docs/STRUCTURE.md, docs/DIAGRAMS.md, README.md (Multi-Spec Features), CLAUDE.md (Architecture) |
core/initiative-orchestration.md |
docs/COMMANDS.md (Initiative Management), docs/REFERENCE.md, docs/STRUCTURE.md, docs/DIAGRAMS.md, CLAUDE.md (Architecture) |
core/dispatcher.md |
CLAUDE.md (Architecture), docs/STRUCTURE.md, README.md (Context-Aware Dispatch) |
core/mode-manifest.json |
CLAUDE.md (Architecture, Mode Architecture — update mode count), docs/STRUCTURE.md |
initiative-schema.json |
docs/REFERENCE.md (Spec Structure), docs/STRUCTURE.md |
New core/*.md (not in table) |
docs/STRUCTURE.md, determine target docs from module content |
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.
- 1mo ago First seen · 197 lines · 0 tokens per session scan A 3ae0f32827ab
docs-sync is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,636 tokens. 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.
Other commands, from other repositories
skill-creator
Create or update an OpenCode skill using the bundled skill-creator workflow.
skill-registry
Rebuild the OpenCode skill registry for the current project and installed skills.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
test-map
/test-map Generate full report for current project /test-map [path] Generate report for a specific directory /test-map --format=html Output as HTML file (default) /test-map --format=md Output as Markdown /test-map --open Generate HTML and open in browser (if tool available).
architect
You are a multi-role software architect. You operate through strict personas and a strictly-validated execution chain where each step is checked before the next. You give honest assessments, not flattery. You challenge every feature request for clarity, consistency, scalability, testability, and security. Your goal is…
generate
/generate jwt --sub user123 --role admin --exp 24h /generate jwt --alg RS256 --sub api-client --exp 7d /generate jwt --decode eyJhbGciOi... /generate keypair --alg RS256 /generate apikey --prefix sk /generate uuid --count 10 /generate password --length 32 /generate secret --length 64 --encoding base64 /generate hash…