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 Miosa-osa/OSA --skill evidence-vault-chain-of-custodygit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/evidence-vault-chain-of-custody)<a href="https://agentmods.dev/skills/miosa-osa/osa/evidence-vault-chain-of-custody"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/evidence-vault-chain-of-custody/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/miosa-osa/osa/evidence-vault-chain-of-custody"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/evidence-vault-chain-of-custody.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 | $0.00137 | $0.01329 |
| Opus 5.5 | $0.00055 | $0.00532 |
| Sonnet 5.5 | $0.00027 | $0.00266 |
| Haiku 4.5 | $0.00014 | $0.00133 |
Grade A, and why
evidence-vault-chain-of-custody 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Vault & Chain of Custody
Derived from T3MP3ST's src/evidence/ (Apache-2.0). The core principle: a
claim is only as strong as its provenance. Prose is not evidence.
1. The provenance-strict verification gate
A finding may be marked verified ONLY when backed by real tool output. The
gate is honest by construction — it never invents provenance, and it states why
it blocked:
- Tool evidence types that count:
output,command,response,request,log,file— each with non-empty content. A human note or a narrative paragraph iscontext, not proof. - Zero tool evidence → FAIL with reason: "no tool-output evidence — provenance-strict requires a finding be backed by real tool output, not prose".
- Severity must be earned: asserting
criticalorhighwith zero evidence of any kind is an overclaim and fails the gate. - Typed provenance:
none(no evidence at all),context(notes only),tool(real output). Onlytoolpasses.
Apply the same gate to your own work: before you report a finding to the operator, list the exact tool receipt (command output, HTTP pair, log line) that backs it. No receipt → report it as a lead, not a confirmed finding.
2. Chain-of-custody records
Every acquired artifact gets a record with these fields:
id, caseId, targetId, name, source, collectedAt, receivedAt,
sha256, sizeBytes, collector, transfer, verified, redactedMetadata
Rules the record enforces:
sha256is computed at acquisition and re-verified on read (verifiedflag) — integrity is checked, not assumed.collectedAt(when the artifact was taken) andreceivedAt(when the vault accepted it) are separate timestamps; a gap is part of the record.- Duplicate artifact names within one acquisition are rejected — a vault that silently dedups is a vault that loses evidence.
- Metadata is redacted at acquisition time (
redactedMetadata), not later. - Acquisition outcomes are typed:
collected | cancelled | permission-denied | collection-failed. Permission errors are their own outcome — never retried as if they were transient.
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.
- 1mo ago First seen · 123 lines · 137 tokens per session scan A 860249d7f85a
evidence-vault-chain-of-custody is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 137 tokens to every session and 1,329 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
unit-converter
Converts between common units of measurement including temperature, distance, and weight.
code-review
Reviews code changes for quality, security, and best practices.
tui-design
This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets…
bun-development
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.
worker-mcp-orchestrator
Guides the coordinator agent on how to orchestrate, delegate to, and supervise local worker agents using the worker-mcp server.
clack
Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.