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 svy04/ballast --skill proof-standardgit clone --depth 1 https://github.com/svy04/ballastWrote 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/svy04/ballast/proof-standard)<a href="https://agentmods.dev/skills/svy04/ballast/proof-standard"><img src="https://agentmods.dev/badge/skills/svy04/ballast/proof-standard.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.00781 |
| Opus 5 | $0.00022 | $0.00391 |
| Sonnet 5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
proof-standard 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 8d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proof standard
External claims about a product come from evidence, not from memory, enthusiasm, or the roadmap. The failure mode this prevents: shipping confident copy about features that don't exist.
The truth file
memory/PRODUCT-TRUTH.md (run brain-init to create it) has three sections:
- Implemented — with evidence (code path, test, screenshot) and a date
- Not implemented — explicitly listed, so absence is a fact rather than a gap
- Permanently excluded — decided against; copy must never imply it
Claims may be sourced only from Implemented.
One truth file per subject you make claims about, split by what kind of evidence is available — code you can read versus someone else's system or word. Name the evidence class at the top of each file, and never let two classes share a section: a line you can settle by opening a path and a line that rests on a vendor's statement do not carry the same weight, and a shared section hides which one you are holding.
Four code states — never blended
| State | Meaning |
|---|---|
implemented |
The code exists |
wired |
Connected end-to-end (UI → backend → effect) |
operational |
Running in production with real data |
verified |
Tested, with evidence you can point to |
Copy that says "we do X" requires operational or better. "X is available" requires at least wired. Everything else is roadmap language — clearly future-tense, clearly conditional. Mixing these states in one sentence is how honest teams end up lying.
Rules
- Truth file first. Before any capability claim, open the truth file. No entry → no claim; register an open question instead of guessing.
- Evidence and dates on every entry. "It works" is not an entry. "Import wired end-to-end, e2e test passing, 2026-08-01,
tests/import.spec.ts" is. - Product changes → truth file first, copy second. Never the reverse order.
- Internal is external. The deck you show an investor, the answer you give a partner — same standard. There is no audience for unproven claims.
- Absence claims too. "We never store X" is a capability claim about the negative — it also needs a truth-file entry with evidence.
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.
- 8d ago First seen · 50 lines · 44 tokens per session scan A 59bbdafd9831
proof-standard is a skill published in the GitHub repository svy04/ballast (71 stars, last pushed 13d ago), licensed MIT. It adds 44 tokens to every session and 781 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…