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 kalpmodi/akira --skill recongit clone --depth 1 https://github.com/kalpmodi/akiraWrote 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/kalpmodi/akira/recon)<a href="https://agentmods.dev/skills/kalpmodi/akira/recon"><img src="https://agentmods.dev/badge/skills/kalpmodi/akira/recon/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/kalpmodi/akira/recon"><img src="https://agentmods.dev/badge/skills/kalpmodi/akira/recon.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 | $0.00095 | $0.01629 |
| Opus 5 | $0.00048 | $0.00814 |
| Sonnet 5 | $0.00019 | $0.00326 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
recon 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recon Phase - Router
Reconnaissance is the most important phase - the attack surface you find here directly determines what you can exploited. This router loads only the technique files your manifest requires.
Technique library: ~/.claude/skills/recon/tech/
Phase 0: Smart Intake
source ~/.claude/skills/_shared/phase0.sh
source ~/.claude/skills/_shared/signals.sh
p0_init_vars "$1"
p0_state_gate "HARVEST" || exit 0
p0_read_memory
# Recon is first phase - no intel relay from prior phases
State gate:
WIDE- run full pipeline (all MUST + SHOULD items)DEEP- targeted only: r01, r02, r03, r04, r05 against active hypothesis surface; mark r06-r09 skippedWRAP- drain queued manifest items only; no new discoveryHARVEST- exit immediately
Execution Manifest
After Phase 0, build manifest based on STATE and hypothesis content:
jq '.scalpel.active_manifest = {
"phase": "recon",
"items": [
{"id":"r01","tech":"asn-subdomain.md","desc":"ASN + passive subdomain + CT + brute","priority":"MUST","status":"pending"},
{"id":"r02","tech":"live-hosts.md","desc":"httpx live probe + favicon + port scan","priority":"MUST","status":"pending"},
{"id":"r03","tech":"urls.md","desc":"URL archive mining + JS analysis","priority":"MUST","status":"pending"},
{"id":"r04","tech":"github.md","desc":"GitHub/GitLab dorking + TruffleHog","priority":"SHOULD","status":"pending"},
{"id":"r05","tech":"cloud-buckets.md","desc":"S3/GCS/Azure/Firebase bucket discovery","priority":"SHOULD","status":"pending"},
{"id":"r06","tech":"takeover.md","desc":"subdomain takeover detection","priority":"SHOULD","status":"pending"},
{"id":"r07","tech":"osint.md","desc":"Google dorking + Shodan/Censys tech intel","priority":"SHOULD","status":"pending"},
{"id":"r08","tech":"dns-advanced.md","desc":"AXFR zone transfer + NSEC walk + passive DNS","priority":"SHOULD","status":"pending"},
{"id":"r09","tech":"scanners.md","desc":"FOFA/Netlas/LeakIX/CriminalIP queries","priority":"IF_TIME","status":"pending"},
{"id":"r10","tech":"tls.md","desc":"JARM/JA4+ TLS fingerprinting","priority":"IF_TIME","status":"pending"},
{"id":"r11","tech":"supply-chain.md","desc":"dependency confusion recon","priority":"IF_TIME","status":"pending"},
{"id":"r12","tech":"wayback.md","desc":"Wayback CDX advanced mining","priority":"SHOULD","status":"pending"},
{"id":"r13","tech":"recontfw.md","desc":"reconFTW orchestration pipeline","priority":"IF_TIME","status":"pending"},
{"id":"r14","tech":"output.md","desc":"write interesting_recon.md + phase-end + intel relay","priority":"MUST","status":"pending"}
]
}' $SESSION > /tmp/s.json && mv /tmp/s.json $SESSION
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- tech/asn-subdomain.md 5.9 KB
- tech/cloud-buckets.md 2.7 KB
- tech/dns-advanced.md 4.9 KB
- tech/github.md 2.6 KB
- tech/live-hosts.md 3.6 KB
- tech/osint.md 3.0 KB
- tech/output.md 6.4 KB
- tech/recontfw.md 2.6 KB
- tech/scanners.md 3.4 KB
- tech/supply-chain.md 3.4 KB
- tech/takeover.md 2.7 KB
- tech/tls.md 2.7 KB
- tech/urls.md 3.4 KB
- tech/wayback.md 3.4 KB
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 · 120 lines · 95 tokens per session scan A 2cd6bc149806
recon is a skill published in the GitHub repository kalpmodi/akira (21 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,629 once invoked, about $0.0005 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 skills, from other repositories
hunt-llm-ai
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration viatool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling…
performing-aws-privilege-escalation-assessment
Performing authorized privilege escalation assessments in AWS environments to identify IAM misconfigurations that allow users or roles to elevate their permissions using Pacu, CloudFox, Principal Mapper, and manual IAM policy analysis techniques.
performing-cloud-penetration-testing-with-pacu
Performing authorized AWS penetration testing using Pacu, the open-source AWS exploitation framework, to enumerate IAM configurations, discover privilege escalation paths, test credential harvesting, and validate security controls through systematic attack simulation.
conducting-cloud-penetration-testing
This skill outlines methodologies for performing authorized penetration testing against AWS, Azure, and GCP cloud environments. It covers understanding the shared responsibility model for testing scope, leveraging cloud-specific attack tools like Pacu and ScoutSuite, exploiting IAM misconfigurations, testing for SSRF…
performing-kubernetes-penetration-testing
Kubernetes penetration testing systematically evaluates cluster security by simulating attacker techniques against the API server, kubelet, etcd, pods, RBAC, network policies, and secrets. Using tools.
conducting-full-scope-red-team-engagement
Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities.