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 agentmods add skills/soliestre/estregenesis/echo-modenpx skills add SoliEstre/EstreGenesis --skill echo-modegit clone --depth 1 https://github.com/SoliEstre/EstreGenesisWrote 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/soliestre/estregenesis/echo-mode)<a href="https://agentmods.dev/skills/soliestre/estregenesis/echo-mode"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/echo-mode.svg" alt="Measured on agentmods" 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 | $0.00177 | $0.01356 |
| Opus 5 | $0.00088 | $0.00678 |
| Sonnet 5 | $0.00035 | $0.00271 |
| Haiku 4.5 | $0.00018 | $0.00136 |
Grade A, and why
echo-mode 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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/echo-mode — mirror the local chat to the board (remote-control)
Bridges an agent's local client conversation (Claude Code / IDE / terminal) with the board's real-time conversation channel, both directions, so a human watching the board can also drive the agent through it. Full spec: Constellation.md §13.26. This skill is the SSoT for the runtime discipline; the echo-emit.cjs hooks (when installed) mechanize the outbound mirror.
Invocation + levels
/echo-mode off|on|mirror|status [agentId] — no agentId targets the invoking agent; targeting another is main-authority gated.
| Level | Mirrors (local → board) |
|---|---|
| off | nothing |
| on | the human's prompt + the assistant's turn-final text + selection prompts (conversation echo) |
| mirror | everything in on + live progress (tool calls, steps, run boundaries) + thinking narration/summary, streamed as the turn runs (chat-gateway / Telegram-bot feel) |
Board→local drive works at both on and mirror — only the outbound richness differs. On any change, announce EchoModeState { agentId, level, provenance } to the board (idempotent) so the dashboard badges the agent and renders its channel as a live conversation.
Protocol when enabled (§13.26.1–.2)
Local → board (mirror out):
- After each assistant turn, emit the turn's user-facing text to this agent's board channel as a
TEXT_MESSAGE(streamingTEXT_MESSAGE_START/_CONTENT/_ENDif the client can stream). Both levels. - Emit the human's local prompt that opened the turn as
UserPrompt { source:'user', text }. Do not re-emit a prompt that arrived from the board — it is already there; just quote it locally (below). mirroronly — stream live progress as the turn runs: tool calls →TOOL_CALL_*cards, steps →STEP_*, run boundaries →RUN_STARTED/_FINISHED, and thinking narration → short statusTEXT_MESSAGE/STEPlines + a turn-end thinking summary. Not raw verbatim chain-of-thought (too verbose, no host thinking-hook) — progress + narration + summary.
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.
- 5d ago First seen · 54 lines · 177 tokens per session scan A a98d4788ea01
echo-mode is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed today), licensed Apache-2.0. It adds 177 tokens to every session and 1,356 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
update-agent-context
This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…
watercooler-onboarding
Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…
ppgp
Portable Persistent Goal Protocol for long-running coding-agent work. Use when starting, resuming, handing off, distilling, or closing a substantial software goal across long sessions, context compaction, agent replacement, or other Agent Skills-compatible coding-agent environments.
search-threads
Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.
watercooler-health
Check watercooler system health — MCP server, baseline graph (T1), git auth, GitHub rate limit, and daemons. Use when syncs break or anything in the watercooler stack behaves unexpectedly.
recall
Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".