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 drillnowgit 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/drillnow)<a href="https://agentmods.dev/skills/soliestre/estregenesis/drillnow"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/drillnow/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/soliestre/estregenesis/drillnow"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/drillnow.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 | $0.00085 | $0.00960 |
| Opus 5 | $0.00043 | $0.00480 |
| Sonnet 5 | $0.00017 | $0.00192 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
drillnow 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 9d 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.
/drillnow — clear the top blocker, now
Where /roundnext sweeps the whole queue (breadth), /drillnow picks the single highest-priority blocked item and spends the turn actually trying to clear it (depth). A drill ends in exactly one of two states: the blocker is gone and the work has started, or the blocker is proven uncllearable right now and the queue is re-prioritized around that proof. "Still blocked, unchanged" is not a valid exit.
Procedure
1. Target selection — load board truth (board_state_get or state.json) and pick the highest-priority blocked: true planned item. Priority = board order unless a rationale says otherwise; skip items whose blocker is a user decision gate (those belong to the decisions panel, not to drilling — verify the panel entry exists, then take the next candidate). Announce the target in one line.
2. Blocker decomposition — restate the blocker as a concrete condition ("what exactly must become true?"), then split it into parts by who/what can move each: this-side-doable / other-party / environment / time. Recorded blockReasons are often coarser than reality — decomposition routinely reveals a this-side-doable part nobody registered.
3. Active clearing attempts (in escalating order of cost; stop at first success):
- Re-verify — is the blocker already gone? (The dependency may have shipped, the precondition met by unrelated work.)
- This-side prerequisite work — execute the doable parts now (collect the evidence the gate requires, build the reproduction, prepare the artifact the other party is waiting on).
- Alternative route — can the item proceed in a reduced or re-ordered form that does not touch the blocked part? (Partial start beats full wait when the partial result is durable.)
- Tool/environment substitution — missing tool: try installing it, or find an equivalent (a manual procedure, a different binary, a degraded-but-sufficient mode).
- Escalated nudge — for other-party blockers, move up the §13.20 ladder one tier (polite ping → explicit reminder + ETA query → hard ETA) with the drill's findings attached (what this side has prepared makes a nudge concrete instead of nagging).
- §13.18 gates hold throughout: no loss/external-publish/genuine-fork action as a "clearing attempt" — those route to the decisions panel.
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.
- 9d ago First seen · 35 lines · 85 tokens per session scan A 1c946396d189
drillnow is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 85 tokens to every session and 960 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
specflo-auto
Use when the user wants an unattended specflo run — "auto mode", "autopilot", "run it on its own", "keep going without me", "don't stop to ask" — map that to specflo auto. It is an explicit, per-invocation opt-in that drives the pipeline across phase boundaries without the ask-first pause. Do NOT use for the normal…
discovery-question-form
Structured clarification form for unresolved material requirements.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.