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-reflect-on-run)<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-reflect-on-run"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-reflect-on-run/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-reflect-on-run"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-reflect-on-run.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 | $0.00581 |
| Opus 5 | $0.00000 | $0.00291 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
sruja-reflect-on-run 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sruja: Reflect on agent run
Use this after an sruja agent loop, sruja agent apply, or sruja agent run --mode apply completes. This command guides your editor agent to distill lessons into agent memory.
Prerequisites
- Repo root is the workspace root (
-r .). - A recent run exists under
.sruja/agent/runs/<run_id>/facts_bundle.json.
Steps
-
Locate the latest run bundle
- List
.sruja/agent/runs/and open the newestfacts_bundle.json. - Note
run_id, verification step outcomes, and any drift/lint facts referenced.
- List
-
Read current memory
- Open
.sruja/agent_memory.json(or runsruja agent history -r . -f json). - Avoid duplicating existing
guardrail_adviceentries.
- Open
-
Reflect (narrative only)
- Summarize: what was attempted, what passed/failed verification, what should change next time.
- Optional: pipe
facts_bundle.jsonto local LLM via Sruja enrichment pattern:jq -c . .sruja/agent/runs/<run_id>/facts_bundle.json | ollama run llama3 - Do not treat model narrative as reviewed architecture truth.
-
Record learnings
- For each actionable guardrail:
sruja agent record -r . \ -c "<short context>" \ -H "<what was tried>" \ -o success|failed \ -g "<guardrail for future agents>" \ --hitl-kind precedent|correction|guardrail - Or call MCP
sruja_record_learningwith the same fields.
- For each actionable guardrail:
-
Curate
sruja agent curate -r .- Apply merges/updates only after human review (
sruja agent merge,agent update,agent delete --force).
- Apply merges/updates only after human review (
-
Optional: team process
- If the learning is stable policy, add a Decision Record under
.sruja/decisions/or update editor rules /sruja-architectureskill—not only agent memory.
- If the learning is stable policy, add a Decision Record under
References
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 · 54 lines · 0 tokens per session scan A 59b1a443fa77
sruja-reflect-on-run is a command published in the GitHub repository sruja-ai/sruja (24 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 581 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.
Other commands, from other repositories
memory
Long-term memory operations for the project.
instinct-import
Import instincts from external sources.
learn
Extract patterns and learnings from current session.
update-memory
Check and update CLAUDE.md memory based on changes to skills, commands, agents, and hooks.
rb-refresh
A command that rebuilds RepoBrain's knowledge base for the current workspace. RepoBrain is a tool that keeps searchable project information for an agent.
kb-ingest
Ingest external material into Sources/ inside the bound project KB, then update registry, index, and daily note as needed.