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.
npx agentmods add commands/cheney369/devora/buildgit clone --depth 1 https://github.com/cheney369/DevoraWhat 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 | $0.00019 | $0.00651 |
| Opus 5 | $0.00010 | $0.00326 |
| Sonnet 5 | $0.00004 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
build 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 2d 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 — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devora Build
User input
$ARGUMENTS
- Run
devora status --json,devora govern status --json,devora govern drift --json,devora change requirement status --json, anddevora quality status --json. Verify that every Governance scope recorded by the active Change is current and complete, its captured company policies and exceptions still match, selected Skills remain active, and the requirement baseline is confirmed with no source drift; resolve blockers before Build. Then rundevora change setup build --json. Readchange.md, optionaltasks.md, relevant project context and Skills, the generated validation matrix, and the real target files. - Verify that material technical and business controls from Design can be honored. If implementation evidence invalidates a decision or a material source changes, register the new evidence, return to Design, resolve the clarification, and reconfirm the baseline before continuing Build.
- Implement in dependency order and stay within allowed paths. Never modify protected paths or broaden scope to clean up a legacy exception. Pre-existing baseline work is input, not this Change's output.
- Run
devora change audit --jsonduring implementation. Resolve unexpected or protected-path changes before proceeding. If the user genuinely expands scope, usedevora change expand --reason <reason>; it preserves the original baseline. - Execute every required governance and type-policy validation. Prefer
devora quality run <id> --command <quoted-command> --timeout <seconds> --provider <runner> --environment <environment> --target <code-path> --jsonfor bounded local commands so complete output is retained automatically; classify a non-zero result as blocked only with concrete environment evidence. Record manual and external evidence explicitly withdevora change validate <id> --result <result> --execution <automatic|manual|external> --provider <tool-or-reviewer> --target <code-path> --risk <scope/finding> --control <scope/control> --evidence <observation> --artifact <report-or-url> --command <command> --environment <environment> --json, omitting fields that do not apply. Useblockedornot_runfor unavailable environments—neverpassed. External passed/failed results require a provider, and local report references must exist. The evidence package is generated automatically. - Keep
change.mdand tasks current with behavior, deviations, residual risk, and recovery details. For a cross-repository Change, register the producer/consumers and write a versioneddevora change contract; keep it proposed until parties confirm it. Add a handoff only for an independently operating consumer. - Run
devora change complete build --json; it rejects stale Skills, scope violations, and failed, blocked, or pending required checks. A high-risk Change is not complete merely because unit tests pass. Otherwise leave Build active with one exact resume action.
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.
- 2d ago First seen · 22 lines · 19 tokens per session scan A 623f192e1b8d
build is a command published in the GitHub repository cheney369/Devora (255 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 651 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.