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 skills/svy04/ballast/reportnpx skills add svy04/ballast --skill reportgit 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/report)<a href="https://agentmods.dev/skills/svy04/ballast/report"><img src="https://agentmods.dev/badge/skills/svy04/ballast/report.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.00536 |
| Opus 5 | $0.00024 | $0.00268 |
| Sonnet 5 | $0.00010 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report — a rule that never fires is a question, not a decoration
Every delivery is logged — rule ids, counts and sizes only, never prompt text — to ~/.claude/ballast/log.jsonl. This skill turns that log into decisions: keep, fix, or prune. Without it a catalog only ever grows, and every injected character of a dead rule is paid for by the work.
Steps
- Run the aggregation:
node "$CLAUDE_PLUGIN_ROOT/hooks/scripts/ballast-rules.mjs" --report(find the path viaclaude plugin listif the variable is not set). It prints fires per rule, last-fired dates, blocks, rules present in the log but gone from the catalog, and — the load-bearing list — catalog rules that have never fired. - Read the never-fired list as symptoms, not verdicts. A rule can be silent for three different reasons, with three different fixes:
- Wrong-language keywords — the user types Korean, the keywords are English. Fix the keywords (pin skill), don't prune.
- Safe-by-default — a danger block that never fired may be doing its job. Keep, and say why.
- Dead weight — a rule about work the user no longer does. Propose pruning.
- Read the top of the table too. A rule firing on most messages is either genuinely always-relevant (should it be
always: true, or is it too generic a keyword spamming every turn?) — propose the tightening, with the numbers. - Propose changes one at a time, apply only on approval. The user is the author of their catalog; the report is evidence, not authority.
Honesty
- An empty log is reported as exactly that, with its candidate causes (new install / no matches yet /
BALLAST_NO_LOG=1) — never as "everything works". - Fire counts measure delivery, not obedience. A rule that fired forty times was placed in front of the model forty times; whether it was followed is a different question this log cannot answer.
Part of ballast — foundations first, every solved path kept, done means checks pass.
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.
- 6d ago First seen · 28 lines · 49 tokens per session scan A 237cba2d21cf
report is a skill published in the GitHub repository svy04/ballast (71 stars, last pushed 11d ago), licensed MIT. It adds 49 tokens to every session and 536 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…