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/briefinggit 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 | $0.00500 |
| Opus 5 | $0.00000 | $0.00250 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
briefing 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 2d 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.
What it actually says
gnosys briefing
Generate a project briefing: memory state summary, categories, recent activity, and top tags.
Usage
gnosys briefing
gnosys briefing <projectNameOrId>
gnosys briefing --project <id>
gnosys briefing --directory /path/to/project
gnosys briefing --all
gnosys briefing --json
Options
| Option | Description |
|---|---|
-p, --project <id> |
Project ID (auto-detects if omitted) |
-a, --all |
Generate briefings for all projects |
-d, --directory <dir> |
Project directory for auto-detection |
--json |
Output as JSON |
Project resolution
For a single-project briefing (without --all):
- Positional
projectNameOrId— matched by ID first, then by registered name --project <id>- Current working directory auto-detection (optional
--directory)
Output modes
All projects (--all, human): section per project with name and summary.
All projects (--all, JSON):
{ "count": 2, "briefings": [...] }
Single project (human): heading, directory, memory counts, categories, recent activity, top tags, summary.
Single project (--json): full briefing object from generateBriefing.
Errors
| Condition | Message |
|---|---|
| Central DB unavailable | Central DB not available. |
| Positional name not found | Project not found: "<name>". Run 'gnosys projects'... |
| No project detected | No project specified and none detected. |
| Project ID not found | Project not found: <id> |
| Other errors | Error: <message> |
Failure paths set process.exitCode = 1 and return through finally.
Validation
cd gnosys-public
npm run cli -- briefing --help
npx vitest run src/test/briefing-command-handler.test.ts
Related commands
gnosys projects— list registered projectsgnosys status— broader project/system status viewsgnosys ambiguity— cross-project query ambiguity check
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.
- 2d ago First seen · 72 lines · 0 tokens per session scan A f260158ae2ae
briefing is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 500 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.
build
Run full verification pipeline.
generate-rules
Generate development rules and standards into RULES.md.
feedback
File a plugin-capability-gap note, or flush queued notes to GitHub issues.
prd
Generate a Product Requirements Document for an team squad. Business-facing artifact. Sensors and evals gate.