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.
git clone --depth 1 https://github.com/Zts0hg/codexspecWrote 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/zts0hg/codexspec/update-workflow-diagrams)<a href="https://agentmods.dev/commands/zts0hg/codexspec/update-workflow-diagrams"><img src="https://agentmods.dev/badge/commands/zts0hg/codexspec/update-workflow-diagrams/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/zts0hg/codexspec/update-workflow-diagrams"><img src="https://agentmods.dev/badge/commands/zts0hg/codexspec/update-workflow-diagrams.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 | $0.00016 | $0.00371 |
| Opus 5.5 | $0.00006 | $0.00148 |
| Sonnet 5.5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
update-workflow-diagrams 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 10d 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.
What it actually says
Repository Workflow Diagram Maintenance
This is repository-maintainer tooling, not a command installed into user projects. Use it for changes to this repository's workflow diagrams and their README assets.
User Input
$ARGUMENTS
Workflow
Read the selected checkout's AGENTS.md/CLAUDE.md, constitution and configuration.
Before writes, load internal/command_templates/fragments/workspace-routing.md
and use its ready output workspace throughout. Read the selected workspace's
internal/workflow_diagrams/README.md and follow its complete update procedure;
it is the shared authority for source files, regeneration, inspection and recovery.
Use the configured interaction language when reporting results.
Translate catalog text using the Shared translation rules section of
internal/references/doc-translation.md and docs/i18n/glossary.yml. The Markdown
translation selectors are not catalog inputs. Preserve approved wording where its
meaning is unchanged; review every affected locale for fidelity and natural usage.
Map the requested change to the canonical template, catalog or layout overrides. Keep generated locale files as outputs. Rebuild all eight editable diagrams and sixteen themed images, validate freshness and README references, and inspect actual renders. Adjust language-specific geometry or wrapping when needed; do not omit meaning or blindly shrink text to fit. Follow existing authorization for visual acceptance, and do not treat command success as proof of semantic/readability checks.
Report changed concepts/locales, actual checks and visual outcomes, outstanding limitations, and absolute paths to the requested previews. This command does not stage, commit, merge, push or release; an enclosing authorized workflow owns those steps after the update is complete.
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.
- 10d ago First seen · 40 lines · 16 tokens per session scan A 34d614252dfd
update-workflow-diagrams is a command published in the GitHub repository Zts0hg/codexspec (6 stars, last pushed 9d ago), licensed MIT. It adds 16 tokens to every session and 371 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-17.
Other commands, from other repositories
xberg-ocr
Extract scanned documents with OCR.
index
Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.
app-factory
Create a scalable Flask application using the factory pattern with blueprints and configuration management.
views
Create Django views with proper structure and best practices.
generate-docs
Generate project documentation from code and AIContext artifacts — reference (internal technical), guide (user-facing), or both.
author-config-workbook
Wraps agents/config-workbook-author/AGENT.md. Compiles the BA's capstone handoff: the 10-section configuration workbook (Org Profile, Objects + Fields, Record Types + Page Layouts, Validation Rules, Permissions + Sharing, Automation, UI + Lightning Pages, Reports + Dashboards, Data Migration, UAT + Cutover) where…