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/cheney369/DevoraWrote 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/cheney369/devora/review)<a href="https://agentmods.dev/commands/cheney369/devora/review"><img src="https://agentmods.dev/badge/commands/cheney369/devora/review/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/cheney369/devora/review"><img src="https://agentmods.dev/badge/commands/cheney369/devora/review.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 | $0.00023 | $0.00478 |
| Opus 5.5 | $0.00009 | $0.00191 |
| Sonnet 5.5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
review 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devora Review
User input
$ARGUMENTS
- Run
devora status --json,devora govern status --json,devora govern drift --json, anddevora change requirement status --json. Verify that every Governance scope recorded by the active Change is current and complete, captured company policies and exceptions still apply, selected Skills are active, registered sources still match the confirmed baseline, and anylimitedunknowns remain explicit. Then rundevora change setup review --json. Readchange.md, optional tasks/evidence/handoff, relevant project context, and the implementation diff or current files. - Review independently. Check requested behavior, scope, regressions, data and permission safety, technical controls, business controls, and consistency with confirmed project decisions.
- Rerun the smallest sufficient material validations, run
devora change audit --json, and inspect automatic, manual, and external evidence. Confirm security results link to the relevant risk, Control, and checked code scope, and that cross-repository contracts identify producer, consumers, version, and confirmed/implemented status. Record prioritized findings inreview.md; useCHANGES_REQUIREDfor defects andBLOCKEDfor a concrete external dependency. A blocked required environment is not release-ready. - When scope, active Skills, and every required validation pass, run
devora quality gate --jsonand inspect both release-readiness exports. Then rundevora change complete review --result awaiting_human --json. Run with--result approvedonly after the user explicitly approves the reviewed scope and revision; the gate remainsawaiting_approvaluntil then. - Feed material Review learning back with
devora govern feedback, re-govern/revalidate affected scopes or Skills, and resume Review. Recordfeedback-status addressedonly with resolution evidence. Advance cross-repository contracts withcontract-statusinstead of replacing the original contract. After explicit approval, update the outcome and rundevora change close --result approved --json. Never infer approval or hide residual risk.
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 · 20 lines · 23 tokens per session scan A fc7bae77a297
review is a command published in the GitHub repository cheney369/Devora (840 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 478 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
refactor
Systematic code refactoring with smart scope detection.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).