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 skills add nutstrut/default-settlement-verifier --skill settlement-witnessgit clone --depth 1 https://github.com/nutstrut/default-settlement-verifierWrote 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/skills/nutstrut/default-settlement-verifier/settlement-witness)<a href="https://agentmods.dev/skills/nutstrut/default-settlement-verifier/settlement-witness"><img src="https://agentmods.dev/badge/skills/nutstrut/default-settlement-verifier/settlement-witness/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nutstrut/default-settlement-verifier/settlement-witness"><img src="https://agentmods.dev/badge/skills/nutstrut/default-settlement-verifier/settlement-witness.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00081 | $0.01607 |
| Opus 5 | $0.00041 | $0.00804 |
| Sonnet 5 | $0.00016 | $0.00321 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
settlement-witness scanned grade A 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS https://defaultverifier.com/settlement-witness \ How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New in 0.1.0: local-first verification. Receipt cryptography is verified entirely on your machine — no network required. Network is optional and only used when you explicitly request remote receipt issuance or resolution.
SettlementWitness
Verify SAR v0.1 settlement receipts locally. Optionally request DefaultVerifier-signed receipts.
When to use
- Before trusting a task-complete claim from another agent
- Before chaining downstream actions to an agent output
- Before using a receipt as evidence
- Before acting on a settlement- or payment-adjacent claim
- When you prefer a local, offline verifier
First run (offline, no network needed)
Run the self-test against all bundled fixtures:
python3 scripts/verify_receipt.py --self-test
Expected output: self_test_passed: true with all six fixtures [OK].
Verify a single receipt
python3 scripts/verify_receipt.py fixtures/sar-v0.1-pass.json
Returns JSON:
{
"valid": true,
"receipt_id": "sha256:...",
"kid": "sar-prod-ed25519-05",
"verdict": "PASS",
"errors": [],
"signer_lifecycle_status": "active",
"trusted_current_production_signer": true,
"trusted_historical_signer": true,
"registry_snapshot_sha256": "2da5285f...",
"offline_verification_note": "Verified offline against the bundled registry snapshot ..."
}
Tamper test (should fail)
python3 scripts/verify_receipt.py fixtures/tampered-receipt.json
Returns valid: false with errors listing the digest mismatch and signature
failure. This proves the verifier actually rejects tampered receipts.
How to interpret results
| Field | Meaning |
|---|---|
valid: true |
Receipt digest and Ed25519 signature both verified |
valid: false |
Receipt failed cryptographic verification |
verdict: PASS |
The signed outcome claims the spec was met |
verdict: FAIL |
The signed outcome claims the spec was not met |
verdict: INDETERMINATE |
The issuer signed an honest uncertainty state |
errors: [...] |
What specifically failed |
signer_lifecycle_status |
The signer's bundled-registry-snapshot lifecycle: active, retired, reserved, documented_non_operational_duplicate, legacy_unclassified, wrong_profile, or unknown |
trusted_current_production_signer |
true only when the key is the current active production signer — a retired key's historical signature can still be valid: true with this false |
trusted_historical_signer |
true when the key is eligible for historical verification (active, retired, or legacy-unclassified) |
registry_snapshot_sha256 |
SHA-256 of the bundled registry snapshot this run verified against |
offline_verification_note |
States this was verified against the bundled snapshot only — not a live-registry freshness claim |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 6.4 KB
- EGRESS.md 1.8 KB
- fixtures/sar-v0.1-current-kid03.json 530 B
- fixtures/sar-v0.1-current-kid05.json 537 B
- fixtures/sar-v0.1-fail.json 419 B
- fixtures/sar-v0.1-indeterminate.json 429 B
- fixtures/sar-v0.1-pass.json 416 B
- fixtures/tampered-receipt.json 628 B
- keys/sar-keys.json 8.6 KB
- scripts/registry_snapshot.py 12 KB runs code
- scripts/verify_receipt.py 11 KB runs code
- SECURITY.md 3.0 KB
- spec/canonicalization.md 3.4 KB
- tests/test_registry_lifecycle.py 7.8 KB runs code
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.
- 9d ago First seen · 186 lines · 81 tokens per session scan A db49f31b4ce3
settlement-witness is a skill published in the GitHub repository nutstrut/default-settlement-verifier (0 stars, last pushed 6d ago), licensed MIT. It adds 81 tokens to every session and 1,607 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.