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 sk-communicationgit 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/sk-communication)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-communication"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-communication/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/sk-communication"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-communication.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.04633 |
| Opus 5 | $0.00015 | $0.02316 |
| Sonnet 5 | $0.00006 | $0.00927 |
| Haiku 4.5 | $0.00003 | $0.00463 |
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 8d 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 — 317 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 .opencode/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 (.opencode/skills/system-skill-advisor/mcp-server/config/route-exclusions.json), so the recommender never surfaces it and you invoke it by hand.
Two lanes
The skill adapts an explanation on three axes. Lane A moves one of them; Lane B moves the other two.
| Lane A — Projection | Lane B — Explanation | |
|---|---|---|
| Axis | Register: the same content in plainer words | Modality (prose → visual) and depth (assumed knowledge) |
| Acts on | An existing byte stream of agent output | A topic, or the prior reply, explained anew |
| Produces | A display-only re-render of that stream | A new diagram, tree, or artifact |
| Reaches a model? | May call a local or hosted model | In-context only |
| Gating | Off by default; egress rules apply | Always available by command; no enablement flag |
| Entry point | /rewrite:response, /rewrite:response-by-external-agent |
/rewrite:explain-visually |
What ships with it
60 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.
- benchmark/README.md 1.5 KB
- benchmark/reports/advisor-routing-smoke-2026-08-12.json 1.2 KB
- benchmark/reports/README.md 1.3 KB
- changelog/v1.0.0.0.md 2.2 KB
- changelog/v1.1.0.0.md 2.1 KB
- cli-communication-projection/.gitignore 52 B
- cli-communication-projection/bin/cli-output-wrapper.mjs 7.0 KB runs code
- cli-communication-projection/bin/external-cli-project.mjs 3.6 KB runs code
- cli-communication-projection/bin/local-project.mjs 3.3 KB runs code
- cli-communication-projection/docs/configuration.md 5.6 KB
- cli-communication-projection/docs/enablement.md 7.1 KB
- cli-communication-projection/docs/install.md 1.9 KB
- cli-communication-projection/docs/privacy.md 1.4 KB
- cli-communication-projection/docs/rollback.md 2.9 KB
- cli-communication-projection/docs/runbook.md 4.2 KB
- cli-communication-projection/docs/support-matrix.md 1.2 KB
- cli-communication-projection/enablement.local.json.example 151 B
- cli-communication-projection/package-lock.json 39 KB
- cli-communication-projection/package.json 2.7 KB
- cli-communication-projection/README.md 4.1 KB
- cli-communication-projection/src/clients/display.ts 2.6 KB runs code
- cli-communication-projection/src/clients/index.ts 1.0 KB runs code
- cli-communication-projection/src/clients/README.md 1.2 KB
- cli-communication-projection/src/clients/sidecar.ts 2.0 KB runs code
- cli-communication-projection/src/clients/types.ts 4.1 KB runs code
- cli-communication-projection/src/config/enablement.ts 2.6 KB runs code
- cli-communication-projection/src/config/index.ts 517 B runs code
- cli-communication-projection/src/config/local-provider.ts 11 KB runs code
- cli-communication-projection/src/context/index.ts 639 B runs code
- cli-communication-projection/src/context/README.md 981 B
- cli-communication-projection/src/context/selector.ts 11 KB runs code
- cli-communication-projection/src/contracts/common.ts 4.6 KB runs code
- cli-communication-projection/src/contracts/context.ts 4.2 KB runs code
- cli-communication-projection/src/contracts/error-record.ts 1.4 KB runs code
- cli-communication-projection/src/contracts/errors.ts 2.3 KB runs code
- cli-communication-projection/src/contracts/event.ts 3.4 KB runs code
- cli-communication-projection/src/contracts/evidence.ts 6.5 KB runs code
- cli-communication-projection/src/contracts/exact-original.ts 3.1 KB runs code
- cli-communication-projection/src/contracts/fixture.ts 1.9 KB runs code
- cli-communication-projection/src/contracts/index.ts 3.6 KB runs code
- cli-communication-projection/src/contracts/projection.ts 3.4 KB runs code
- cli-communication-projection/src/contracts/prompt.ts 2.6 KB runs code
- cli-communication-projection/src/contracts/provider.ts 3.4 KB runs code
- cli-communication-projection/src/contracts/README.md 2.4 KB
- cli-communication-projection/src/contracts/registry.ts 5.1 KB runs code
- cli-communication-projection/src/contracts/validate-event.ts 11 KB runs code
- cli-communication-projection/src/contracts/validate-evidence.ts 17 KB runs code
- cli-communication-projection/src/contracts/validate-policy.ts 18 KB runs code
- cli-communication-projection/src/contracts/validator-utils.ts 7.9 KB runs code
- cli-communication-projection/src/core/assembler.ts 12 KB runs code
- cli-communication-projection/src/core/assembly-input.ts 7.1 KB runs code
- cli-communication-projection/src/core/assembly-output.ts 6.3 KB runs code
- cli-communication-projection/src/core/assembly-types.ts 4.9 KB runs code
- cli-communication-projection/src/core/index.ts 1.1 KB runs code
- cli-communication-projection/src/core/normalizer.ts 4.3 KB runs code
- cli-communication-projection/src/core/README.md 1.4 KB
- cli-communication-projection/src/doctor/checks.ts 19 KB runs code
- cli-communication-projection/src/doctor/doctor.ts 1.8 KB runs code
- cli-communication-projection/src/doctor/index.ts 1012 B runs code
- cli-communication-projection/src/doctor/README.md 1.3 KB
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.
- 8d ago First seen · 317 lines · 31 tokens per session scan A 9c58b80ddd47
sk-communication is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 4,633 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 2026-09-03.
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…
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…
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.