Borrowing it
Nothing to install: this file belongs to IgorGanapolsky/ThumbGate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/IgorGanapolsky/ThumbGate/main/.claude/skills/evidence-first-answer/SKILL.mdgit clone --depth 1 https://github.com/IgorGanapolsky/ThumbGateWrote 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/igorganapolsky/thumbgate/evidence-first-answer)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/evidence-first-answer"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/evidence-first-answer/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/igorganapolsky/thumbgate/evidence-first-answer"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/evidence-first-answer.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 | $0.00067 | $0.01089 |
| Opus 5 | $0.00034 | $0.00544 |
| Sonnet 5 | $0.00013 | $0.00218 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade B, and why
evidence-first-answer scanned grade B with 2 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 10d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
1. **Do not restate.** Do not add caveats to the previous answer. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Any number inside `reports/gtm/*` that isn't backed by a same-file `curl` output How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence-First Answer — The "Are You Sure?" Discipline
When to invoke
- Any user question that contains: "why didn't", "how come no", "are we", "what's our", "did we", "how much", "revenue", "money", "customers", "conversion", "traffic", "leads", "sales"
- Any pushback that contains: "are you sure?", "really?", "is that right?", "verify", "prove it"
- Before writing any phrase that implies traction or its absence
The hard discipline (4 steps, no skipping)
1. Date-check every number you're about to cite
# For any doc you're about to quote:
git log -1 --format='%ai %s' -- <path>
grep -E "^Updated:|^Status:|2026-" <path> | head -5
If the doc's last-updated date is older than 14 days, treat its numbers as historical, not current. Say "as of " explicitly.
2. Distinguish "plan" from "telemetry"
Words/phrases that mean the number is a forecast, not an actual:
- "30-day revenue plan showed..."
- "Modeled target..."
- "Projected..."
- "If we hit..."
- Any number inside
docs/MONETIZATION_EXEC_SUMMARY_*.mdpast line 30 - Any number inside
reports/gtm/*that isn't backed by a same-filecurloutput
Words/phrases that mean the number is measured:
- "
getBillingSummaryreturned..." - "
curl /v1/billing/summaryJSON..." - "Stripe-reconciled charges..."
- A bash code block with the actual command + output
When in doubt, run revenue-truth skill — query the live endpoint.
3. The "what would change my mind" test
Before submitting an answer, write down: "What single piece of evidence would prove this answer wrong?" Then go look for that evidence. If you find it, rewrite. If you can't find a falsifier, your hypothesis is probably too vague — refine it.
4. State your uncertainty explicitly
End every answer that touches commercial state with:
- What I verified: (curl outputs, file dates, commit SHAs)
- What I'm assuming: (and why)
- What would change the answer: (the specific check the user can run)
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.
- 10d ago First seen · 94 lines · 67 tokens per session scan B a15508b95be3
evidence-first-answer is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,089 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (strips warnings and disclaimers, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agentguard
Runtime guardrails for AI coding agents. Stop loops, budget overruns, retry storms, and timeouts before they burn money. Zero dependencies, local-first, MIT licensed.
crm-pipeline-playbook
How to answer pipeline, renewal, and account-health questions using the CRM tools.
deciding-who-decides
Decides who holds authority for a change — the agent at the edge or a human gate — by matching decision rights to reversibility, evidence, and consequence, and names the escalation trigger. Use when an agent could act on something irreversible, trust-bearing, or thinly evidenced. Do not use for trivial reversible…
staying-on-mission
Tests the current work against a written, lasting mission anchor and forces one choice, re-anchor, escalate, or stop. Use when an agent keeps finishing tasks but the work drifts from the goal, scope creeps, the same action repeats in a loop, or standards slip one small step at a time. Do not use for a tiny edit with…
verifying-final-artifacts
Verifies the delivered artifact a consumer actually receives (a figure, chart, PDF, SVG, screenshot, compiled build, or deployed response) by regenerating it fresh and directly observing the output, not the source that produces it, and ends in one honest verdict. Use when the deliverable is a produced artifact and…
closing-stale-packets
Brings an abandoned or half-filled change packet to an honest terminal state by completing it, closing it with a recorded rationale, or deleting it. Use when ng status flags a scaffold or invalid packet, a long session left a draft behind, or work was abandoned mid-packet. Do not use for an actively in-progress…