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/fiale-plus/fiale-claude-plugins/team-pushgit clone --depth 1 https://github.com/fiale-plus/fiale-claude-pluginsWrote 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/team-push)<a href="https://agentmods.dev/commands/fiale-plus/fiale-claude-plugins/team-push"><img src="https://agentmods.dev/badge/commands/fiale-plus/fiale-claude-plugins/team-push.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 | $0.00017 | $0.00729 |
| Opus 5 | $0.00009 | $0.00365 |
| Sonnet 5 | $0.00003 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade B, and why
brain-team-push 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote a personal atom from ~/brain/atoms/ to the team vault. Use this when you want to share an insight that wasn't auto-routed during synthesis.
Steps
1. Read config
cat ~/.claude/brain/config.json
If team.enabled is false, say: "Team vault not configured. Run /brain-team-setup first." and stop.
2. Identify atom to promote
If slug was provided as argument: look it up directly:
cat ~/brain/atoms/<slug>.md
If no argument: list atoms by reference count and ask:
python3 -c "
import json
from pathlib import Path
index = json.loads(Path.home().joinpath('.claude/brain/atoms-index.json').read_text())
sorted_atoms = sorted(index, key=lambda x: x.get('reference_count', 1), reverse=True)
for a in sorted_atoms[:20]:
print(f\"{a['reference_count']:3d}x {a['slug']}\")
"
Ask:
"Which atom to promote? Enter slug or number from list above:"
Read the selected atom file:
cat ~/brain/atoms/<slug>.md
3. Choose format and destination
Show the atom content. Ask:
"Promote as:
- pattern — recurring convention or approach
- decision — architectural or design choice
- gotcha — blocker or non-obvious solution [default: pattern]"
4. Confirm and promote
Show:
Promote to team vault?
Slug: <slug>
Format: <format>
Dest: <team_vault_path>/<format>/<slug>.md
Mode: <auto_promote_mode>
Ask: "Proceed? [y/n]"
If yes:
python3 -c "
import sys; sys.path.insert(0, '${CLAUDE_PLUGIN_ROOT}/bin')
import synthesize, json, re
from pathlib import Path
atom_path = Path.home() / 'brain/atoms/<slug>.md'
text = atom_path.read_text()
# Extract title from frontmatter
title_match = re.search(r'title:\s*(.+)', text)
title = title_match.group(1).strip() if title_match else '<slug>'
# Extract content (below frontmatter)
content = re.sub(r'^---\n.*?\n---\n', '', text, flags=re.DOTALL).strip()
config = synthesize.load_config()
synthesize.write_team_doc(
config['team']['vault_path'],
'<format>',
title,
content,
config['team'].get('auto_promote_mode', 'commit')
)
print(f'Promoted: {config[\"team\"][\"vault_path\"]}/<format>/<slug>.md')
"
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.
- 4d ago First seen · 104 lines · 17 tokens per session scan B 92d4fff1f4eb
brain-team-push is a command published in the GitHub repository fiale-plus/fiale-claude-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 729 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.
architect
System design with Memory-based coordination for scalable architectures.
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.
grill-me
Run an interactive one-question-at-a-time oral drill for research defence or active-recall study, escalating around weak answers and ending with a study sheet. Use when the user asks to be grilled, quizzed, or prepared for a viva, job talk, seminar, or exam. Not for a written critique; use $devils-advocate or a review…
thoughts_init
Initialize thoughts system for current repository.