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 skillgit 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/skill)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/skill"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/skill/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/skill"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/skill.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 | $0.00026 | $0.03930 |
| Opus 5.5 | $0.00010 | $0.01572 |
| Sonnet 5.5 | $0.00005 | $0.00786 |
| Haiku 4.5 | $0.00003 | $0.00393 |
Grade A, and why
sk-communication 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 16d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communication Projection
Make supported CLI and agent output read like careful plain English, across Claude, Codex, Pi, OpenCode, Devin, and Cursor, while leaving the canonical event stream, transcript, tool data, and model context byte-for-byte unchanged. Every unsafe or failed path returns the exact original. The implementation is the @portable-cli/communication-projection package under .skilled/skills/sk-communication/cli-communication-projection/; this skill routes you to the right part of it and enforces its invariants.
Projection is off by default for everyone. Nothing rewrites CLI output until an operator opts in on their own machine, by setting COMMUNICATION_PROJECTION_ENABLED or by adding a git-ignored enablement.local.json at the package root. Every activation path checks isProjectionEnabled() first. This skill is also held out of advisor routing on purpose. sk-communication is on the advisor route-exclusions denylist (.skilled/skills/system-skill-advisor/runtime/config/route-exclusions.json), so the recommender never surfaces it and you invoke it by hand.
One lane
This skill does one thing: it re-renders an existing byte stream of agent output in plainer words, without changing the register's content, and returns the exact original whenever it cannot. It acts on a message that already exists; it never composes new material.
It carried a second lane until this release — an explanation lane that turned a topic into a diagram at a chosen depth. That lane was retired. What it produced was a fenced Mermaid block, which the terminals it ran in display as source text rather than as a picture, and the runtimes that can publish a rendered page now do so natively. The projection lane keeps this skill's whole risk profile, and that profile is what the enablement flag and the egress rules exist to contain.
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.
- 16d ago First seen · 268 lines · 26 tokens per session scan A 498026cf0aeb
sk-communication is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (37 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 3,930 once invoked, about $0.0001 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 2026-10-01.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…