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.
git clone --depth 1 https://github.com/ViryaZheng/recomby-geoWrote 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/commands/viryazheng/recomby-geo/03-gap)<a href="https://agentmods.dev/commands/viryazheng/recomby-geo/03-gap"><img src="https://agentmods.dev/badge/commands/viryazheng/recomby-geo/03-gap/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/commands/viryazheng/recomby-geo/03-gap"><img src="https://agentmods.dev/badge/commands/viryazheng/recomby-geo/03-gap.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 | $0.00058 | $0.01797 |
| Opus 5 | $0.00029 | $0.00898 |
| Sonnet 5 | $0.00012 | $0.00359 |
| Haiku 4.5 | $0.00006 | $0.00180 |
Grade A, and why
03-gap 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 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.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
03 · Gap & Opportunity — Prioritize What to Build
The decision skill. Takes raw baseline data + business context and returns: "these are the N content pieces, in this order, with this expected impact, because of this reason."
The framework: CITE × CORE-EEAT (borrowed from
aaron-he-zhu/seo-geo-claude-skills taxonomy):
- Citability — can we be cited as a primary source?
- Intent match — does our angle match the searcher's job-to-be-done?
- Trustworthiness — do we have E-E-A-T signals (experience, expertise, authority, trust)?
- Expansion — is this query a wedge into a larger query cluster?
Inputs
clients/<slug>/brand_context.jsonclients/<slug>/visibility_baseline.json
Output
clients/<slug>/content_priorities.json— validates againstschemas/content_priorities.schema.json.
Procedure
Step 1 — Build the candidate set
Every target_query from brand_context becomes a candidate. Augment with:
- Queries surfaced in
layer_2_market_reality.real_user_questionsthat weren't intarget_queries. - Queries from
layer_3_value_gaps[*].opportunityif phrased as a question.
Step 2 — Score each candidate (CITE × CORE-EEAT)
For each candidate, compute:
| Dimension | How to score |
|---|---|
| Citability | Does brand_context have first-party data, expert POV, or unique methodology that can be cited? +1 to +3. |
| Intent match | Does the brand's product directly serve the JTBD behind this query? +1 to +3. |
| Trustworthiness | Does the brand have E-E-A-T signals (author bios, credentials, citations elsewhere) for this topic? +0 to +3. |
| Expansion | Does winning this query wedge open a cluster (5+ adjacent queries)? +0 to +3. |
| Current pain | From baseline: absent (+3), contested (+2), winning-but-fragile (+1), winning-stable (0). |
| Difficulty (penalty) | Strong incumbent (-2), generic category leader entrenched (-3), policy-restricted topic (-3). |
Sum → expected_impact.score (clamp to 1–10).
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 · 183 lines · 58 tokens per session scan A feffe164207d
03-gap is a command published in the GitHub repository ViryaZheng/recomby-geo (453 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,797 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
commit-all
Stage and commit all current changes with a single message. Auto Git Push will pick up and push to origin within 30s.
check
Run the full local quality gate — TypeScript check, build, dependency audit (prod-only), skill registry validate. Fast pre-commit / pre-suggestdeploy sweep.
registry
Refresh the skills registry — regenerate SHA-256 manifest from disk, then validate. Run after editing any file under .agents/skills/.
onboard
/anty:onboard — QUEST-Based Conversational Interview.
quickstart
/anty:quickstart — 5-Minute Quick Onboarding to First Action.
review
/anty:review — 5-Question Review Engine.