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 SoliEstre/EstreGenesis --skill talkagit 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/talka)<a href="https://agentmods.dev/skills/soliestre/estregenesis/talka"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/talka.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 5.1 | $0.00080 | $0.00857 |
| Opus 5 | $0.00040 | $0.00428 |
| Sonnet 5 | $0.00016 | $0.00171 |
| Haiku 4.5 | $0.00008 | $0.00086 |
Grade A, and why
talka 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/talka — talk-about elicitation (conversational knowledge intake)
/eg-interview presses a request into a delegable brief in a few batched rounds. /talka covers the cases where that press fails or harms: the knowledge is tacit (the requester knows more than they can answer directly), the topic is early (no concrete request exists yet to brief), or the relationship cost of interrogation exceeds the information gain. The output is not a brief — it is accumulated judgment material, materialized at the end.
1. When to run (and when not to)
Run when a review or judgment is coming up whose quality depends on what the requester knows — domain constraints, history, taste, unstated red lines — and direct questioning would under-extract it. Do NOT run when a concrete request already exists (that is /eg-interview's job), when the decision is already framed (that is Hyperbrief's job), or when the needed facts are measurable from the workspace (measure instead of asking — a question answerable by reading a file is not a conversation topic).
2. Conversation discipline
- Topic anchor, loose leash. Name the topic once at the start. Drift is allowed — tangents are where tacit knowledge lives — but return to the anchor when a tangent stops yielding.
- At most one question per turn, often zero. Prefer contributions: state an observation, a hypothesis, or a tentative reading of the situation, and let correction do the extraction. People correct a wrong statement more readily — and more precisely — than they answer an open question. This is
/eg-interview's default-and-confirm, slowed to conversational pace. - Follow the requester's energy. Deepen where they lean in; the thing they volunteer unprompted is usually the thing the checklist would have missed.
- Mirror periodically. Restate what you heard in your own words ("그러니까 X 라는 말씀이죠") — mishearing surfaces immediately instead of surviving into the judgment.
- Contribute genuinely. Never feign ignorance to farm answers; a conversation where one side is performing curiosity reads as an interrogation with extra steps.
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 · 35 lines · 80 tokens per session scan A 86cab8553358
talka is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 80 tokens to every session and 857 once invoked, about $0.0004 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?".