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/sruja-ai/srujaWrote 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/sruja-ai/sruja/sruja-workflow-aidlc)<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-workflow-aidlc"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-workflow-aidlc/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/sruja-ai/sruja/sruja-workflow-aidlc"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-workflow-aidlc.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 | $0.00019 | $0.00609 |
| Opus 5 | $0.00010 | $0.00304 |
| Sonnet 5 | $0.00004 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
sruja-workflow-aidlc 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are driving one phase of an AI-DLC workflow integrated with Sruja. Obey AGENTS.md and docs/AIDLC_INTEGRATION.md.
The user must provide a phase: inception, construction, or operations.
Shared setup (all phases)
- Confirm repo root (
-r .). - If no workflow exists, run:
sruja workflow init -r . --title "<short title>" --with-aidlc --install-aidlc-rules - Otherwise ensure rules are installed:
sruja workflow install-rules -r . - Load AIDLC steering from
.aidlc/aidlc-rules/and rule details from.aidlc-rule-details/(followcore-workflow.md). - Before large edits, run:
If it fails, fix listedsruja workflow status -r . --checkmissing/aidlc_missingitems before proceeding.
Phase — inception
- Ensure
inception/scope.mdand runsruja workflow record-impact -r . --id <id>whentarget_elementsare set. - Produce AIDLC artifacts under
inception/aidlc-docs/(never mix app code into aidlc-docs). - Optional grounded review:
sruja workflow design-review -r . --id <id> - When ready:
sruja workflow approve -r . --id <id> --phase inceptionthensruja workflow advance.
Phase — construction
- Gate must pass (
workflow status --check); inception must be approved in strict mode. - Use
.cursor/commands/sruja-plan-feature.mdfor task-layerconstruction/task-plan.md. - Link proposals in
construction/linked_proposal_ids.json; usesruja propose create --workflow-id <id>. - App code in repo root or
workspace/; run project tests /just check(ormake check) as appropriate. - Approve construction phase when artifacts and proposals are ready.
Phase — operations
- Ensure
operations/deploy-scope.jsonexists. - Run
sruja drift -r . -a repo.srujaand resolve violations before operations approval. - Approve operations when deploy scope and drift are clean.
Audit
After significant stage steps:
sruja workflow audit -r . --id <id> --event "stage complete: <name>"
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 · 59 lines · 19 tokens per session scan A 963eb56a8f3b
sruja-workflow-aidlc is a command published in the GitHub repository sruja-ai/sruja (24 stars, last pushed 3d ago), licensed Apache-2.0. It adds 19 tokens to every session and 609 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
arrange-workspace-flow-technical-context
Phase 4 Technical context of arrange-workspace-flow.
plan
Planning, brainstorming, architecture, and refactoring strategies.
xray
Zero-config X-ray of this repo's real architecture — map, living docs, and evolution feed. No rules required.
check
Fail on NET-NEW architecture violations only — the same ratchet ArchSteer runs in CI, run right now.
plan-feature
Plan and implement a feature through the VibeFrame model (context → declare → implement → link → validate).
review-drift
Walk the VibeFrame drift inbox and resolve each finding (fix / accept / dismiss).