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/reflectgit 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/reflect)<a href="https://agentmods.dev/commands/fiale-plus/fiale-claude-plugins/reflect"><img src="https://agentmods.dev/badge/commands/fiale-plus/fiale-claude-plugins/reflect.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 | $0.00024 | $0.00698 |
| Opus 5 | $0.00012 | $0.00349 |
| Sonnet 5 | $0.00005 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade B, and why
brain-reflect 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 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.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesize patterns across recent sessions into a weekly insight note. Run at end of week or whenever you want a retrospective.
Steps
1. Load config and locate session notes
cat ~/.claude/brain/config.json
Get vault_path. List available session notes:
ls VAULT_PATH/_sessions/ | sort
2. Determine scope
Ask the user:
"How many days back should I look? Default is 7 (last week). Enter a number or press Enter."
If Enter or "default", use 7. Call this DAYS.
Calculate date range: today minus DAYS through today.
3. Read session notes in range
For each date in range that has a file in _sessions/, read the full file.
Also read VAULT_PATH/Polaris/top-of-mind.md if it exists.
4. Synthesize patterns
Using your own reasoning across session content, produce a reflection covering:
Theme distribution — which primary themes appeared and how often (building / debugging / researching / planning / configuring)
Wins — concrete things that got done (from outcome=done sessions, knowledge items with destination=project)
Recurring blockers — anything that appeared more than once as a blocker
Durable learnings — the most reusable insights across the week (look at personal atoms created)
Alignment signal — overall trend; any drift from Polaris top-of-mind?
Suggested Polaris updates — based on what you actually worked on vs what top-of-mind.md says, suggest specific edits
Thread worth picking up — the most interesting unexplored area from the week
Next week focus — concrete recommendation for what to prioritize
5. Write weekly note
python3 -c "from datetime import date; d=date.today(); print(f'{d.year}-W{d.isocalendar()[1]:02d}')"
Write to VAULT_PATH/weekly/YYYY-Www.md. If file already exists, prepend a new section (same-week re-runs accumulate, don't replace).
Format:
# Week YYYY-Www Reflection
_<start_date> – <end_date> · <N> sessions · <N> days_
## Theme distribution
<theme>: N · <theme>: N · ...
## Wins
- ...
## Recurring blockers
- ...
## Durable learnings
- ...
## Alignment: <high|medium|low|mixed>
<1-2 sentences on alignment trend>
## Suggested Polaris updates
- [ ] <specific suggested edit to top-of-mind.md>
- [ ] ...
## Thread worth picking up
<the most interesting unexplored thread>
## Next week focus
<concrete recommendation>
---
_Generated by /brain-reflect on <today>_
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 · 105 lines · 24 tokens per session scan B ab88f12e0816
brain-reflect is a command published in the GitHub repository fiale-plus/fiale-claude-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 698 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
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
statusbar-theme
Switch the status-bar color theme (graphite / twilight / linen).
statusbar-preview
Render every style × theme combination using your real cached data.
statusbar-reset
Wipe the status-bar config back to defaults.
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.