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 blisspixel/recon --skill recon-catalog-roundgit clone --depth 1 https://github.com/blisspixel/reconWrote 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/blisspixel/recon/recon-catalog-round)<a href="https://agentmods.dev/skills/blisspixel/recon/recon-catalog-round"><img src="https://agentmods.dev/badge/skills/blisspixel/recon/recon-catalog-round/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/blisspixel/recon/recon-catalog-round"><img src="https://agentmods.dev/badge/skills/blisspixel/recon/recon-catalog-round.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 | $0.00052 | $0.00907 |
| Opus 5.5 | $0.00021 | $0.00363 |
| Sonnet 5.5 | $0.00010 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
recon-catalog-round 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catalog round
Requires a recon source checkout. Paths below refer to its root. This maintainer
skill is separate from the frozen portable plugin candidate.
Read docs/catalog-maintenance.md and docs/data-handling-policy.md, then the
selected round protocol in validation/README.md.
Admit the round
First distinguish review of existing artifacts from a new formal round. Candidate review can proceed without a full frozen bundle, but must disclose missing provenance and cannot claim independent or contract-bound evaluation. Establish whether the rows are development or holdout before mining candidates. A review-only request permits findings and proposed patches, not catalog edits or publication. Do not collect missing evidence without a collection request.
For a new formal round, use the supplied private plan, corpus, and manifest. If missing, return to corpus planning; do not silently construct a convenience sample. Confirm the user requested collection. Report the frozen count, CT setting, concurrency, destination of private outputs, and that DNS and default MTA-STS requests can be visible before collection begins. Respect any predeclared protected-main or publication gate in the round contract.
Run --help rather than inventing preflight flags: rank preparation has an
explicit preflight; generic preparation and scan validate inputs internally.
Collection
uses validation.scan, not a shell loop interpolating domain strings. Its
--ct choice must match the manifest; direct probes remain off. Do not bypass
manifest or implementation-digest failures, append new rows, silently retry a
holdout, or increase concurrency to finish faster. A failed or incomplete round
remains incomplete; keep the original artifacts and declare any permitted rerun.
For an existing-result task, do not invoke collection at all.
Pass the frozen --min-count and --concurrency explicitly. For a new
independent non-drift round, use --no-compare unless an exact prior was
declared; the scan otherwise chooses the latest local run. Drift requires its
explicit prior and sidecar and must not disable comparison.
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.
- 1mo ago First seen · 78 lines · 52 tokens per session scan A 6e1c1c4a545b
recon-catalog-round is a skill published in the GitHub repository blisspixel/recon (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 52 tokens to every session and 907 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-06.
Other skills, from other repositories
github-secret-hunting
Find leaked API keys, tokens, and credentials in public GitHub repositories.
google-dorks-catalog
High-precision Google dorks for exposed configs, secrets, and credentials -- real-world validated.
metabigor
Use when operating the metabigor CLI for OSINT recon and infrastructure mapping without API keys. Covers finding network ranges from an ASN, org, domain, or IP (net); enumerating subdomains from certificate logs (cert); enriching IPs with ports/CVEs via Shodan InternetDB (ip); searching public GitHub code for secrets…
osint-methodology
Comprehensive OSINT methodology for external red-team operations and authorized attack-surface assessments. Covers the 5-stage recon pipeline (seed discovery, asset expansion, enrichment, exposure analysis, reporting), asset-graph discipline with 29 asset types, severity rubric (CRITICAL/HIGH/MEDIUM/LOW/INFO)…
conducting-external-reconnaissance-with-osint
Conducts external reconnaissance using Open Source Intelligence (OSINT) techniques to map an organization's external attack surface without directly interacting with target systems. The tester gathers information from public sources including DNS records, certificate transparency logs, search engines, social media…
offensive-osint
Operational arsenal for authorized external red-team and bug-bounty recon. Concrete probes, wordlists, regexes, dorks, curl one-liners for: subdomain enum, GraphQL/Swagger/REST discovery, identity fabric (Entra/Okta/ADFS/Google/SAML/M365 deep — Teams/SharePoint/OneDrive), cloud bucket enum (S3/GCS/Azure), CDN/WAF…