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/proticom/gnosys/reflectgit clone --depth 1 https://github.com/proticom/gnosysWhat 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 | $0.00000 | $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
reflect 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 yesterday.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gnosys reflect
Reflect on an outcome to update memory confidence and create relationships in the central Gnosys database.
Usage
gnosys reflect "deploy succeeded"
gnosys reflect "auth refactor failed" --failure --memory-ids mem-1,mem-2
gnosys reflect "hotfix shipped" --notes "rolled back within 10 minutes" --confidence-delta 0.15 --json
Arguments
| Argument | Description |
|---|---|
outcome |
Short description of what happened |
Options
| Option | Description |
|---|---|
--memory-ids <ids> |
Comma-separated memory IDs to relate to the outcome |
--failure |
Mark the outcome as failure (default: success) |
--notes <text> |
Additional reflection notes |
--confidence-delta <n> |
Custom confidence delta (e.g. 0.1 or -0.2) |
--json |
Output reflection result as JSON |
Prerequisites
Requires the central Gnosys database with better-sqlite3 available.
Request mapping
The handler builds sandbox params:
outcome— from positional argumentsuccess—!opts.failurememory_ids— split/trim from--memory-idswhen setnotes— from--noteswhen setconfidence_delta— parsed float from--confidence-deltawhen set
Sent via handleRequest with id: "cli-reflect" and method: "reflect".
Human output
Reflection recorded:
ID: refl-abc123
Outcome: deploy succeeded
Memories updated: 2
Relationships created: 3
Confidence delta: +0.10
JSON output
Success emits the sandbox result object via JSON.stringify(result, null, 2).
On failure with --json:
{
"ok": false,
"error": "error message"
}
Errors
- Missing DB driver: install message then exit 1.
- Sandbox error:
Reflect failed: ...then exit 1. - Unexpected exception: JSON or human error, then exit 1.
DB is closed in finally even when errors occur.
Validation
cd gnosys-public
npm run cli -- reflect --help
npx vitest run src/test/reflect-command-handler.test.ts
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.
- yesterday First seen · 89 lines · 0 tokens per session scan A d97685a7774d
reflect is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 15d ago), licensed MIT. 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 2026-08-31.
Other commands, from other repositories
init-project
Configure this project for Obsidian PKM — connects the repo to a vault project folder and writes CLAUDE.md integration directives.
setup
Configure Vault PKM plugin — set vault path, API keys, and verify setup.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
competitive-landscape
Map the competitive landscape for a market or company.