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/speculationnpx skills add SoliEstre/EstreGenesis --skill speculationgit 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/speculation)<a href="https://agentmods.dev/skills/soliestre/estregenesis/speculation"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/speculation.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 | $0.00233 | $0.01778 |
| Opus 5 | $0.00117 | $0.00889 |
| Sonnet 5 | $0.00047 | $0.00356 |
| Haiku 4.5 | $0.00023 | $0.00178 |
Grade A, and why
speculation 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/speculation — who authorizes a speculative lane
/superscalar decides how many lanes. /subscaler decides what each lane runs on. This skill decides who signs off on a speculative one — a lane that starts the likely branch of a gate that has not resolved yet (an approval, a review verdict, a test outcome, an A/B choice), so the result is ready the instant the gate clears.
Speculation is the one dispatch class that spends tokens on work that may be thrown away. That is why it has its own toggle instead of riding the dispatch-aggressiveness one: fanning out more lanes and betting on an unresolved branch fail differently and want to be tuned separately.
Normative spec: Superscalar.md §4. Read it before changing this skill — in particular the two-stage announce and the Andon three elements, which this toggle does not modify.
0. Toggle contract
State = one marker file: .agent/speculation.json → {"mode": "off"|"auto"|"on"|"always", "since": "<date>", "note": "<why>"}. Absent ⇒ off. Read it at dispatch time; never mirror the mode into other settings surfaces — duplicated per-lane bindings have shipped state-convergence bugs.
/speculation off— writeoff(or delete the marker)/speculation auto— writeauto/speculation on— writeon/speculation always— writealways/speculation status— read it back and report the mode plus where it would apply to the work in front of you. A toggle without a read-back is a setting nobody can confirm, and an unconfirmable setting drifts from what its owner believes it to be.
1. What each mode authorizes
| Mode | Low downstream sensitivity (read · analyze · summarize · sandboxed test, inside the worktree) | High downstream sensitivity (interface design, contract change — work largely redone if the prediction was wrong) |
|---|---|---|
off (default) |
no lane | no lane |
auto |
ask per speculation | ask per speculation |
on |
pre-authorized | ask |
always |
pre-authorized | pre-authorized |
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 · 79 lines · 233 tokens per session scan A 371598ddf0a2
speculation is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 233 tokens to every session and 1,778 once invoked, about $0.0012 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?".