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 alexeyshishin/as-skill --skill code-buildgit clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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/alexeyshishin/as-skill/code-build)<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/code-build"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/code-build/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/alexeyshishin/as-skill/code-build"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/code-build.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 | $0.00057 | $0.00476 |
| Opus 5.5 | $0.00023 | $0.00190 |
| Sonnet 5.5 | $0.00011 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
code-build 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.
What it actually says
Skill: /code-build
ORCHESTRATOR. You route work to executing agents by file scope. No code edits in the main loop.
Invocation
/code-build <slug>
Steps
- Find the plan:
swarm-report/<slug>-plan.md. Missing → abort: "Run/code-plan \"<feature>\"first." - Check Blockers in the plan. Any unresolved HIGH → abort and name it. The user must resolve or explicitly waive it.
- Route by scope: read the plan's
affected_files. Match each against the Executing table inAGENTS.md(frontend / backend / devops / mobile). Group files by agent. No match for a file → ask the user which agent owns it. - Spawn the matched exec agents — one
Taskcall each, in parallel when a feature spans several layers (single message, N calls,subagent_type: general-purpose). Prompt each:Answer TERSE. Read
.claude/agents/<scope>.mdand follow it exactly. Plan: swarm-report/-plan.md. Your scope: . If one agent's output changes a contract another needs (e.g. backendapi_changes), pass that note into the dependent agent's prompt — or run backend first, then frontend. - Verify: read each agent's
tests_result. Anystatus: blockedor failing test → do NOT claim success. Report the failures verbatim and stop. Offer/code-build <slug>retry after the fix. - Write
swarm-report/<slug>-build.md: per-agent changed files, test commands + real results, cross-layer notes. - Report to user: status per scope + test results. Quote real output — no "done" without proof.
What ships with it
1 file 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.
- 1mo ago First seen · 35 lines · 57 tokens per session scan A a4cee30bda6d
code-build is a skill published in the GitHub repository alexeyshishin/as-skill (5 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 476 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
obsidian
Comprehensive guidelines for Obsidian.md plugin development including ESLint rules from eslint-plugin-obsidianmd v0.4.2, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, popout window compatibility, community.obsidian.md submission process, and Scorecard optimization. Use…
loop-engineering
Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.
harness-engineering
Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.
wiki-ingest
Use when a PDF, URL, transcript, clipping, or raw note must become source-grounded, linked, governed knowledge in an Obsidian vault.
agent-teams-command
Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require bounded multi-agent command scaled from 5 to 100+ agents.
agentic-engineering
Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.