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/arielshad/balagan-agent/summarizegit clone --depth 1 https://github.com/arielshad/balagan-agentWrote 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/arielshad/balagan-agent/summarize)<a href="https://agentmods.dev/commands/arielshad/balagan-agent/summarize"><img src="https://agentmods.dev/badge/commands/arielshad/balagan-agent/summarize.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.00263 |
| Opus 5 | $0.00003 | $0.00131 |
| Sonnet 5 | $0.00001 | $0.00053 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
summarize 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 3d 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.
This is a copy
100% identical to summarize — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Read all research notes in files/research_notes/ and create an executive summary.
Summary Requirements
1. Executive Overview (1 paragraph)
- What was researched
- Key findings at a glance
- Bottom-line takeaway
2. Key Insights (Bullet Points)
- Top 5-7 most important findings
- Ranked by significance
- Each insight should be actionable
3. Detailed Findings by Topic
For each research note:
- Topic/subtopic covered
- Main findings
- Key sources used
4. Contradictions and Uncertainties
- Areas where sources disagreed
- Information that couldn't be verified
- Topics needing more research
5. Knowledge Gaps
- Questions that couldn't be answered
- Areas with limited information
- Recommended follow-up research
6. Source Quality Assessment
- Most reliable sources found
- Any questionable sources to note
- Overall confidence level
Output
Create two files:
files/reports/executive_summary_[timestamp].txt- 1-page summaryfiles/reports/detailed_findings_[timestamp].txt- Full analysis
Use the report-writer subagent for professional formatting.
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.
- 3d ago First seen · 47 lines · 7 tokens per session scan A d29ff0efb4d8
summarize is a command published in the GitHub repository arielshad/balagan-agent (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 263 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to summarize, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
worktree-merge
Merge the current worktree's work back to master through the 4-gate verification chain and locked rebase.
worktree
Start the session in an isolated git worktree so this agent can work in parallel with other sessions without conflicting.
release-management
Prepares a MockServer release by recommending the release version from Semantic Versioning rules and changelog.md, checking release readiness, and listing the exact Buildkite release parameters. Use when users say "prepare release", "release version", "run the release pipeline", "which version should we release", or…
commit
Commit changes following the full pre-commit workflow (classify, validate, review).
agent-status
Show a status table of all active agent worktrees (created via /worktree), their branch, age, current activity, commit count ahead of master, and rebase-lock status.
review-code
Deep audit of code for correctness, security, testing, and resilience.