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/chhuax/praxis-devosWrote 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/chhuax/praxis-devos/devos-docs-refresh)<a href="https://agentmods.dev/commands/chhuax/praxis-devos/devos-docs-refresh"><img src="https://agentmods.dev/badge/commands/chhuax/praxis-devos/devos-docs-refresh/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/chhuax/praxis-devos/devos-docs-refresh"><img src="https://agentmods.dev/badge/commands/chhuax/praxis-devos/devos-docs-refresh.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 | $0.00478 |
| Opus 5.5 | $0.00000 | $0.00191 |
| Sonnet 5.5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
devos-docs-refresh 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devos-docs-refresh
Refresh existing project documentation using the devos-docs skill.
What this does
- Updates
docs/surfaces.yamlwhen the external surface changes - Updates
docs/codemaps/project-overview.mdto match the current structure - Updates module-level codemap docs when structure or responsibilities change
- Aligns documentation with the current OpenSpec change
Mode
refresh
When to use
Run this command when:
- code structure has evolved
- new modules or surfaces have been added
- existing docs are out of date
- an OpenSpec change is being archived (REQUIRED)
Change-aware refresh (IMPORTANT)
When invoked during an OpenSpec flow, you MUST provide change context:
- active
changeId - OpenSpec artifacts:
- proposal / design / spec / tasks
- changed code paths (if available)
- optional affected module hints
The refresh MUST:
- reflect actual implemented structure after the change
- align with spec and design decisions
- update both:
- project overview
- affected module docs
Implementation
-
Invoke the
devos-docsskill withmode=refresh -
Detect
artifact_language:- prefer
docs/surfaces.yaml - fallback to
AGENTS.md/README.md
- prefer
-
Pass change-aware context into the skill:
- REQUIRED for OpenSpec archive / flow-driven refreshes
- OPTIONAL for general refresh usage outside an active OpenSpec flow
-
Use stable docs routing:
docs/surfaces.yamldocs/codemaps/project-overview.mddocs/codemaps/module-map.md(multi-module)docs/codemaps/modules/<artifactId>.md(deterministic only)
-
Follow Agent Collaboration protocol if using sub-agent
-
MUST consume sub-agent output (no rebuild from scratch)
-
Validate contract BEFORE writing
-
Write all files in a single pass
Constraints
- Refresh is incremental (non-destructive)
- Do not create parallel structures or new CodeMap versions
- Do not write speculative / future-state content
- Must align with actual code and OpenSpec spec
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.
- 2mo ago First seen · 76 lines · 0 tokens per session scan A 48b59c761711
devos-docs-refresh is a command published in the GitHub repository chhuax/praxis-devos (21 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 478 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.
devos-docs-refresh compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| devos-docs-refreshchhuax/praxis-devos | Command | 21 | 6mo ago | Apache-2.0 | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |