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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill hermes-sk-code-opencodegit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/hermes-sk-code-opencode)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/hermes-sk-code-opencode"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/hermes-sk-code-opencode/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/hermes-sk-code-opencode"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/hermes-sk-code-opencode.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 | $0.00060 | $0.04290 |
| Opus 5.5 | $0.00024 | $0.01716 |
| Sonnet 5.5 | $0.00012 | $0.00858 |
| Haiku 4.5 | $0.00006 | $0.00429 |
Grade C, and why
sk-code-opencode scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Keywords: opencode, system-code, typescript, python, shell, rust, jsonc, config, mcp, skill-authoring, agent-authoring, command-authoring, hooks, alignment-verifier, surface-evidence, sk-code --> How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canonical source:
.skilled/skills/sk-code/sk-code-opencode/. This is a generated markdown-only copy so Hermes can load the skill without scanning the canonical directory; readreferences/,assets/andscripts/from the canonical path above.
opencode Surface — System-Code Evidence
Domain evidence and shared workflow doctrine for OpenCode system code (the .skilled/ tree: skills, agents, commands, plugins, MCP servers, config, changelogs, and runtime bridge wiring). This surface owns the implement -> debug -> verify phases through the workflow references below, then slices evidence by the detected language so a TypeScript task never pulls the Python/shell/config guides.
Detection is two-step. First, the surface trigger is work under .skilled/ (including SKILL.md, descriptors, commands, agents, plugins, MCP servers, assets, scripts, and changelogs). Second, once the OpenCode surface is selected, file extensions and local markers select the language trio: .cjs/.mjs/.js -> JavaScript, .ts/.tsx/.mts/.d.ts -> TypeScript, .py plus argparse -> Python, .sh/.bash -> shell, .rs -> Rust, .json/.jsonc/.yaml/.yml plus graph-metadata or spec-folder -> config. For Rust, when no .rs file is present, local Cargo.toml/Cargo.lock markers select it after the OpenCode surface is established; napi-rs and wasm-bindgen vocabulary are additional intent signals, not cross-project surface detectors.
1. WHEN THE HUB BUNDLES THIS
- The task touches
.skilled/system code — a skill, agent, command, plugin, MCP server, or descriptor/config. - The active workflow phase needs a language standard, a language-agnostic organization pattern, a hook contract, an alignment-verification procedure, or an authoring checklist.
- This surface owns edits, tests, and verification through the workflow references; hand off formal findings-first review to
code-reviewand author-side quality gates tocode-quality.
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 · 199 lines · 60 tokens per session scan C 2b87f6bc33a3
sk-code-opencode is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (37 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 4,290 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…