Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add fiale-plus/fiale-claude-plugins/plugin install brainWrote 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/fiale-plus/fiale-claude-plugins/synthesize)<a href="https://agentmods.dev/commands/fiale-plus/fiale-claude-plugins/synthesize"><img src="https://agentmods.dev/badge/commands/fiale-plus/fiale-claude-plugins/synthesize.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 5.1 | $0.00018 | $0.01089 |
| Opus 5 | $0.00009 | $0.00544 |
| Sonnet 5 | $0.00004 | $0.00218 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade B, and why
synthesize scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/brain/config.json How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process pending transcripts, classify insights, and route them to the right layer: project .brain/ docs, personal ~/brain/atoms/, and optional team vault.
Batch limit: process at most 20 sessions per run. If the queue is larger, process the first 20, then report how many remain.
Steps
1. Read config and pending queue
cat ~/.claude/brain/config.json
cat ~/.claude/brain/pending.json
If pending.json is missing or empty, say "No pending sessions." and stop.
If the queue has more than 20 items: "Queue has N sessions — processing first 20. Run /synthesize again for the remainder." Take only the first 20 paths as the working set.
2. For each transcript path in the queue
a. Extract transcript metadata:
python3 -c "
import sys; sys.path.insert(0, '${CLAUDE_PLUGIN_ROOT}/bin')
import synthesize, json
sid, slug, msgs, date = synthesize.parse_transcript('<transcript_path>')
idx = synthesize.read_sessions_index('<transcript_path>')
print(json.dumps({
'session_id': sid,
'project_name': synthesize.project_name_from_slug(slug, idx.get('projectPath', '')),
'project_path': idx.get('projectPath', ''),
'user_messages': msgs,
'session_date': date.isoformat(),
'message_count': idx.get('messageCount', '?'),
'first_prompt': idx.get('firstPrompt', ''),
'git_branch': idx.get('gitBranch', '')
}))
"
b. Check idempotency — skip if already processed:
grep -rl "<!-- session:<session_id> -->" ~/brain/_sessions/ 2>/dev/null
If found, skip this transcript.
c. Read Polaris context (if vault configured):
cat ~/brain/Polaris/top-of-mind.md 2>/dev/null
d. Synthesize — produce a Knowledge JSON object based on user_messages, first_prompt, project_name, git_branch, and top-of-mind content:
{
"summary": "1-2 sentence summary of what happened",
"outcome": "done | in_progress | blocked",
"suggested_next": "what to do next",
"primary_theme": "building | debugging | researching | planning | configuring",
"knowledge": [
{
"destination": "project | personal | team",
"format": "decision | gotcha | pattern | insight",
"title": "Short title (5-10 words)",
"content": "Detailed explanation with context and rationale"
}
]
}
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.
- 5d ago First seen · 129 lines · 18 tokens per session scan B b15ef53349bf
synthesize is a command published in the GitHub repository fiale-plus/fiale-claude-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,089 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
post-task
Execute post-task cleanup, performance analysis, and memory storage.
session-end
Cleanup and persist session state before ending work.
context-stats
Display context window usage and token statistics.
statusbar-doctor
Run cs doctor to diagnose why the status bar isn't showing what you expect.
statusbar
Show current status-bar config and list available styles + themes.
handoff
Create a handoff document for seamless session continuity.