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 afaraha8403/balakit --skill executegit clone --depth 1 https://github.com/afaraha8403/balakitWrote 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/afaraha8403/balakit/execute)<a href="https://agentmods.dev/skills/afaraha8403/balakit/execute"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/execute/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/afaraha8403/balakit/execute"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/execute.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 | $0.00085 | $0.01246 |
| Opus 5.5 | $0.00034 | $0.00498 |
| Sonnet 5.5 | $0.00017 | $0.00249 |
| Haiku 4.5 | $0.00009 | $0.00125 |
Grade A, and why
execute 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 28d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute
Leading words: current first, same-family ok, slug shield, auto-pick stays distinct, this chat does the work.
Workers research. This chat does the work. There is no agent-count flag — pick 2 or 3 from the job (default 3; 2 if the request is small, local, or mechanical).
Operating contract
- Do not auto-start this skill. The user must ask for it.
- Current-for-all is the default. Same family may occupy more than one slot when they chose that.
- Auto-pick is the only path that still requires distinct families.
- Do not invent a model name. Use the live list this harness exposes.
- Never write a spawn identifier in a question, option, chat roster, worker prompt, or take label. Map family → live-list name only in the spawn tool's
modelargument. Current →inherit(or omitmodel). - Workers are read-only. A worker that edits files has failed; discard that take.
- This chat writes after the takes. Do not send writes back to workers.
- If this host cannot spawn a child at all, stop. Auto-pick that cannot gather two families: offer Current-for-all or
deep-deliberation.
Runtime state
EXECUTE_STATE
host: cursor | claude-code | opencode | copilot | codex | other
agents: 2 | 3
roster: unset | Current,OpenAI,…
takes: 0/N
next_action: one action only
Pipeline
Copy these steps into the todo list verbatim. Skip with skip: <reason>.
- Detect the host. Read references/hosts.md. Build the live spawnable model list. Current-for-all does not need two families.
- Set
agentsto 3, or 2 if the request is small, local, or mechanical. If the user named models (or current), use that list (2–5) instead of auto-pick. One named model fills every slot. - Resolve roster: models the user named, or Current for all, or auto-pick, or assign each worker. Announce with display names before spawning.
- Spawn one read-only worker per roster slot. Same prompt. Parallel. Read references/worker-prompt.md.
- Render labeled takes (
[Current],[OpenAI], …). Do not write yet. - This chat merges with
[display name]attribution, does the work, proves the real path.
What ships with it
2 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.
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.
- 28d ago First seen · 126 lines · 85 tokens per session scan A 7c46637f8b60
execute is a skill published in the GitHub repository afaraha8403/balakit (1 stars, last pushed 29d ago), licensed MIT. It adds 85 tokens to every session and 1,246 once invoked, about $0.0003 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 2026-09-18.
Other skills, from other repositories
designing-data-intensive-applications
Apply Martin Kleppmann-inspired data-system rules when designing reliability, scalability, consistency, replication, transactions, streams, or schema evolution.
domain-driven-design-distilled
Apply Vaughn Vernon-inspired lightweight DDD rules when using bounded contexts, subdomains, context maps, and tactical modeling without excess ceremony.
implementing-domain-driven-design
Apply Vaughn Vernon-inspired implementation DDD rules when building aggregates, domain events, repositories, application services, or context integrations.
patterns-of-enterprise-application-architecture
Apply Martin Fowler-inspired enterprise architecture rules when choosing layers, service layers, transaction scripts, domain models, repositories, mappers, or DTOs.
the-pragmatic-programmer
Apply Hunt and Thomas-inspired pragmatic programming rules when improving engineering judgment, feedback loops, DRY knowledge, orthogonality, automation, or adaptability.
working-effectively-with-legacy-code
Apply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.