recon
Use when running reconnaissance on a pentest target, starting phase 1 of an engagement, gathering subdomains, DNS resolution, live hosts, port scan results…
Skill by kalpmodi
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kalpmodi-recon
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/recon
What's inside
- Skill name
recon- Description
- Use when running reconnaissance on a pentest target, starting phase 1 of an engagement, gathering subdomains, DNS resolution, live hosts, port scan results, URL intelligence, JavaScript endpoints, GitHub secrets, cloud buckets, subdomain takeovers, or attack surface mapping. Also use when the user says "run recon", "start recon", "phase 1", "enumerate subdomains", "find attack surface", or "map the target".
- License
- MIT
- Instructions
- 116 lines in SKILL.md · view on GitHub
Files (15)
- SKILL.md
- asn-subdomain.md · tech/
- cloud-buckets.md · tech/
- dns-advanced.md · tech/
- github.md · tech/
- live-hosts.md · tech/
- osint.md · tech/
- output.md · tech/
- recontfw.md · tech/
- scanners.md · tech/
- supply-chain.md · tech/
- takeover.md · tech/
- tls.md · tech/
- urls.md · tech/
- wayback.md · tech/
SKILL.md (first lines)
# 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
```bash
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 skipped
- `WRAP` - drain queued manifest items only; no new discovery
- `HARVEST` - exit immediately
---
## Execution Manifest
After Phase 0, build manifest based on STATE and hypothesis content:
```bash
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
```
---
## Technique Loader Table
Load technique files based on manifest and hypothesis content. Read ONLY what the manifest requires.
| Manifest ID | Technique file | Load when |
|---|---|---|
| r01 | `asn-subdomain.md` | Always (MUST) |
| r02 | `live-hosts.md` | Always (MUST) |
| r03 | `urls.md` | Always (MUST) |
| r04 | `github.md` | SHOULD + GitHub org found OR secrets hypothesis |
| r05 | `cloud-buckets.md` | SHOULD + cloud tech detected OR `cloud_hints.aws=true` |
| r06 | `takeover.md` | SHOULD + CNAMEs to third-party services found |
| r07 | `osint.md` | SHOULD + STATE=WIDE |
| r08 | `dns-advanced.md` | SHOULD + DNSSEC detected OR nameservers look outdated |
| r09 | `scanners.md` | IF_TIME + STATE=WIDE |
| r10 | `tls.md` | IF_TIME + CDN/WAF detected (need origin bypass) |
| r11 | `supply-chain.md` | IF_TIME + JS-heavy frontend OR dev hypothesis |
| r12 | `wayback.md` | SHOULD + large program OR old target domain |
| r13 | `recontfw.md` | IF_TIME + want full automation |
| r14 | `output.md` | Always (MUST - phase-end) |
### Hypothesis-driven reprioritization
| Hypothesis mentions | Reprioritize |
|---|---|
| AWS / GCP / Azure / cloud | r05 -> MUST first, r07 add cloud queries |
| JWT / OAuth / SSO | r03 (JS analysis) -> MUST first, r04 (GitHub) -> MUST |
| Supply chain / dependency | r11 -> MUST |
| SSRF / internal IP | r02 (port scan) -> MUST, r09 (scanners) -> SHOULD |
| Subdomain takeover | r06 -> MUST first |
| No specific hypothesis | Run r01-r14 in order |
---
## Signal Emission Reference
| Discovery | Signal type | Emit when |
|---|---|---|
| New subdomains (batch) | `SURFACE_FOUND` | After merge (r01) |
| Live host found | `SURFACE_FOUND` | Each host (r02) |
| Tech detected | `TECH_DETECTED` | Each framework/cloud (r02) |
| WAF fingerprinted | `WAF_CONFIRMED` | httpx WAF header (r02) |
| Unusual open port | `SURFACE_FOUND` | DB/internal exposed (r02) |
| Verified GitHub secret | `CRED_FOUND` | TruffleHog verified (r04) |
| Open cloud bucket | `SURFACE_FOUND` | Each accessible bucket (r05) |
| AXFR success | `SURFACE_FOUND` | Zone dump (r08) - CRITICAL, emit immediately |
| Subdomain takeover | `VULN_CONFIRMED` | Confirmed fingerprint (r06) |
| Unclaimed npm/pypi | `SURFACE_FOUND` | Each unclaimed package (r11) |
After every `TECH_DETECTED` signal, check correlation rules in plan-engagement Step 6.
---
## Completion Gate + Phase-End
After all MUST manifest items complete, run `p0_completion_gate || exit 1` then read `output.md` for intel relay instructions.
See `output.md` for the full Phase-End protocol: interesting_recon.md generation, session.json write-back, hypothesis calibration, fork candidates, completion gate, and intel relay write.From kalpmodi/akira, MIT.
More from kalpmodi/akira
- 0.552score
plan-engagement
kalpmodi
Use when starting any pentesting engagement, receiving a target domain or IP, saying "new engagement", "start a pentest", "plan this target", or beginning any…
SkillCFreshness: C★ 23Claude Code +9 - 0.491score
zerodayhunt
kalpmodi
Use when hunting for zero-days, backdoors, RCE, supply chain attacks, JWT vulnerabilities, cache poisoning, HTTP smuggling, dependency confusion, source map…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
oauth-attacks
kalpmodi
Use when attacking OAuth 2.0 or OIDC implementations, testing for authorization code interception, PKCE bypass, open redirect chains, token leakage via…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
race-conditions
kalpmodi
Use when testing for race conditions, single-packet attacks, TOCTOU vulnerabilities, limit-bypass via concurrent requests, coupon/voucher reuse, double-spend…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
redteam
kalpmodi
Use when running APT-level red team operations, post-exploitation, lateral movement, credential harvesting, Active Directory attacks (Kerberoasting, DCSync…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
report
kalpmodi
Use when generating a pentest report, writing up findings from a completed assessment, converting triage output into a structured document, or producing an…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
triage
kalpmodi
Use when aggregating pentest findings across all phases, clustering vulnerabilities by severity, prioritizing findings for a report, or surfacing the top…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
ad-attacks
kalpmodi
Use when attacking Active Directory environments, hunting Kerberoastable accounts, AS-REP roasting, DCSync, Pass-the-Hash, Pass-the-Ticket, BloodHound path…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
compact
kalpmodi
Use when context is running long during a pentest engagement, at phase boundaries after completing a full phase, or when the user says "compact", "compress…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
exploit
kalpmodi
Use when running exploitation phase of a pentest, testing for SQL injection, XSS, SSRF, JWT confusion, deserialization, prototype pollution, HTTP smuggling…
SkillDFreshness: D★ 23Claude Code +9 - 0.487score
secrets
kalpmodi
Use when hunting for secrets, API keys, tokens, or credentials on a pentest target, running phase 2 of an engagement, scanning JS files for hardcoded secrets…
SkillDFreshness: D★ 23Claude Code +9 - 0.487score
ctf
kalpmodi
Use when working on CTF (Capture the Flag) challenges, HackTheBox machines, TryHackMe rooms, pwn challenges, reverse engineering, cryptography puzzles…
SkillDFreshness: D★ 23Claude Code +9
Signals
- Stars
- 23
- Forks
- 4
- Open issues
- 0
- Last commit (this folder)
- Apr 25, 2026 (6 months ago)
- Last release
- Apr 25, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kalpmodi/akira
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kalpmodi
- 0.552score
plan-engagement
kalpmodi
Use when starting any pentesting engagement, receiving a target domain or IP, saying "new engagement", "start a pentest", "plan this target", or beginning any…
SkillCFreshness: C★ 23Claude Code +9 - 0.491score
exploit
kalpmodi
Use when running exploitation phase of a pentest, testing for SQL injection, XSS, SSRF, JWT confusion, deserialization, prototype pollution, HTTP smuggling…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
ad-attacks
kalpmodi
Use when attacking Active Directory environments, hunting Kerberoastable accounts, AS-REP roasting, DCSync, Pass-the-Hash, Pass-the-Ticket, BloodHound path…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
triage
kalpmodi
Use when aggregating pentest findings across all phases, clustering vulnerabilities by severity, prioritizing findings for a report, or surfacing the top…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
compact
kalpmodi
Use when context is running long during a pentest engagement, at phase boundaries after completing a full phase, or when the user says "compact", "compress…
SkillDFreshness: D★ 23Claude Code +9 - 0.491score
oauth-attacks
kalpmodi
Use when attacking OAuth 2.0 or OIDC implementations, testing for authorization code interception, PKCE bypass, open redirect chains, token leakage via…
SkillDFreshness: D★ 23Claude Code +9
Cite this page
recon skill. Agent Mart. https://agentmart.dev/skills/kalpmodi-recon (last updated 2026-10-24)