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-corpus-plangit 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-corpus-plan)<a href="https://agentmods.dev/skills/blisspixel/recon/recon-corpus-plan"><img src="https://agentmods.dev/badge/skills/blisspixel/recon/recon-corpus-plan/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-corpus-plan"><img src="https://agentmods.dev/badge/skills/blisspixel/recon/recon-corpus-plan.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 | $0.00047 | $0.00632 |
| Opus 5.5 | $0.00019 | $0.00253 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
recon-corpus-plan 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Corpus planning
This is a repository maintainer skill. It requires a recon source checkout and its validation harnesses; it is not part of the frozen portable plugin candidate. Paths below are relative to that checkout, even if this skill is installed elsewhere.
Read docs/catalog-maintenance.md and docs/data-handling-policy.md first.
Use validation/README.md for the selected preparer's exact input contract;
inspect its plan loader and --help before producing an executable plan.
Define the question before selecting rows
Determine whether the user needs candidate discovery, independent evaluation, or forward-time drift. Record the proposed source, dated revision and digest, selection rule, sample-size budget, strata, and what the result cannot estimate. Do not invent a list of organizations or infer corporate ownership from domains. When only a question is supplied, propose a source and sampling design; a live download or target lookup is a separate action, not part of an offline plan.
Use the existing preparer that matches the question:
- Rank:
validation.prepare_catalog_rank_framefor frozen rank bands and private keyed sampling, including its actual development-exclusion files. - ccTLD:
validation.prepare_catalog_region_framewith frozen IANA and UN M49 inputs. ccTLD membership is not geography or registrant location. - Provider relationship:
validation.prepare_vendor_seed_roundwith archived provider-owned evidence and declared exclusions. A customer label does not establish publication of a particular DNS record. - Drift:
validation.prepare_catalog_drift_roundbinds the exact retained prior result. Repeating a corpus is not independent evaluation. - Other declared strata:
validation.prepare_catalog_roundnormalizes and deduplicates the frame. Itspolicies.exclusionstext does not mechanically exclude prior development data. Verify that exclusion using a supported frame builder or an explicit tested comparison before calling it a holdout.
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 · 56 lines · 47 tokens per session scan A c6d1ff23091a
recon-corpus-plan is a skill published in the GitHub repository blisspixel/recon (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 47 tokens to every session and 632 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…