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/alinotfoundbtw/sounding/githubgit clone --depth 1 https://github.com/alinotfoundbtw/soundingWhat 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 | $0.00016 | $0.00381 |
| Opus 5 | $0.00008 | $0.00191 |
| Sonnet 5 | $0.00003 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
github 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.
What it actually says
Audit and improve the public presence of this repository. Report everything before changing anything, and stop for confirmation before anything irreversible (see the hard rules in CLAUDE.md).
1. Correctness first
Run /check. If the tree does not pass, nothing about presentation matters yet.
2. Verify every public claim
Read README.md line by line against reality:
- Test count — run them and compare
- Rule counts per adapter — count the registries
- Version numbers in examples
- Roadmap markers — is "you are here" on the right line
- Every terminal block — re-run the command and confirm the output still matches
Report each mismatch. Stale numbers in a README are the cheapest possible way to look unmaintained.
3. Repository metadata
Check and propose (do not apply yet):
- Description — one sentence, states the problem, not "a tool for X"
- Topics —
mcp,ai-agents,security,linter,model-context-protocol - Pinned repositories on the profile
- Social preview image
4. Known gaps become issues
Anything real and unfinished gets an issue rather than silence. Currently:
pin/diffsupports MCP only — not skills or prompts, though drift matters more for skills- The playground's browser rendering has never been exercised by anyone
- Prompt rules have no eval layer; only skills have routing analysis
Write each as a problem statement, not a feature request. Do not open an issue for something already fixed.
5. Report
Give me a list of what you would change, grouped by whether it needs my approval. Then wait.
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 · 51 lines · 16 tokens per session scan A 44f81401642e
github is a command published in the GitHub repository alinotfoundbtw/sounding (4 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 381 once invoked, about $0.0001 per session on Opus 5. 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
validate-dependencies
Validate all task dependencies for issues.
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
flow-nexus-auth
Flow Nexus authentication and user management.
validate-prd
Validate an existing PRD against BMAD standards - comprehensive review for completeness, clarity, and quality.
editorial-review-structure
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension.
add-tool
Scaffold a new FreeAgent MCP tool (handler + registration + test) following the repo pattern.