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-evolve-rules-after-miss)<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-evolve-rules-after-miss"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-evolve-rules-after-miss/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-evolve-rules-after-miss"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-evolve-rules-after-miss.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 | $0.00014 | $0.00271 |
| Opus 5 | $0.00007 | $0.00135 |
| Sonnet 5 | $0.00003 | $0.00054 |
| Haiku 4.5 | $0.00001 | $0.00027 |
Grade A, and why
sruja-evolve-rules-after-miss 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 11d 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
Something went wrong with an AI-assisted change (wrong behavior, missed convention, bad architecture). Outer loop: improve the system so it is less likely to repeat.
Work with the user to:
- Characterize the miss — What should have happened vs what happened? Was it ignorance of a rule, missing validation, or ambiguous scope?
- Pick the smallest durable fix among:
AGENTS.md— add a gate, clarify a command, document a workflow step.cursor/rules/sruja-dev.mdc(or a new.mdcrule) — file-type or area-specific constraint.cursor/commands/*.md— if the same long prompt was needed repeatedly- User or repo skills under
.agents/skills/(or project skill paths) — multi-step procedure - Issue / PR templates — acceptance criteria or checklists the agent skipped
- Draft the concrete edit (patch-level: what section or file to add or change). Keep wording short and imperative.
- Verify — Explain how the next agent run would behave differently.
Do not rewrite unrelated docs. One focused improvement beats a broad rewrite.
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.
- 11d ago First seen · 20 lines · 14 tokens per session scan A bf065b442d7f
sruja-evolve-rules-after-miss is a command published in the GitHub repository sruja-ai/sruja (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 14 tokens to every session and 271 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.
check
Fail on NET-NEW architecture violations only — the same ratchet ArchSteer runs in CI, run right now.
xray
Zero-config X-ray of this repo's real architecture — map, living docs, and evolution feed. No rules required.
review-drift
Walk the VibeFrame drift inbox and resolve each finding (fix / accept / dismiss).
plan-feature
Plan and implement a feature through the VibeFrame model (context → declare → implement → link → validate).