akira
01Plugin Claude Code
The AI pentest co-pilot that actually finds bugs. Phase-chained, evidence-gated offensive security skills for bug bounty and authorized pentesting.
Plugin Claude Code
The AI pentest co-pilot that actually finds bugs. Phase-chained, evidence-gated offensive security skills for bug bounty and authorized pentesting.
Instructions file CodexOpenCode
Instructions for kalpmodi/akira, covering akira - ai agent adapter, what akira does, skill index, how to use and phase artifacts.
Cursor rule Cursor
Akira pentest skill suite - activates for security testing, bug bounty, and CTF tasks.
Skill Claude CodeCodex
Use when encountering HTTP 403 Forbidden responses during pentests or bug bounty hunting, testing access control bypasses, trying to reach restricted endpoints, admin panels, or protected API routes. Also trigger when the user says "403 bypass", "bypass forbidden", "access denied bypass", "forbidden page bypass", or…
Skill Claude CodeCodex
Internal utility library - not an invokable skill. Contains phase0.sh (session state, intel relay, memory read) and signals.sh (append-only signal emission). Sourced by all other skills via source /.claude/skills/shared/phase0.sh.
Skill Claude CodeCodex
Use when attacking Active Directory environments, hunting Kerberoastable accounts, AS-REP roasting, DCSync, Pass-the-Hash, Pass-the-Ticket, BloodHound path analysis, LDAP enumeration, GPO abuse, ACL abuse, or full AD domain compromise chains. Also use when the user says "attack AD", "domain compromise", "Kerberoast"…
Skill Claude CodeCodex
Use when auditing cloud infrastructure for misconfigurations, testing AWS IAM privilege escalation, enumerating exposed S3 buckets, attacking GCP service accounts, testing Azure RBAC misconfigs, hunting for exposed Kubernetes API servers, or finding cloud credential leaks in metadata services. Also use when the user…
Skill Claude CodeCodex
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 context", "trim context", or "save tokens". Compresses completed phase outputs while keeping session.json as the authoritative source of truth.
Skill Claude CodeCodex
Use when working on CTF (Capture the Flag) challenges, HackTheBox machines, TryHackMe rooms, pwn challenges, reverse engineering, cryptography puzzles, forensics, web exploitation CTF tasks, OSINT challenges, or steganography. Also use when the user says "CTF", "HackTheBox", "HTB", "TryHackMe", "THM", "pwn this"…
Skill Claude CodeCodex
Use when running exploitation phase of a pentest, testing for SQL injection, XSS, SSRF, JWT confusion, deserialization, prototype pollution, HTTP smuggling, cache poisoning, SSTI, XXE, GraphQL, SAML, LFI, file upload bypass, CORS, WebSocket hijacking, IDOR, mass assignment, account takeover chains, 2FA bypass, or any…
Skill Claude CodeCodex
Use when attacking OAuth 2.0 or OIDC implementations, testing for authorization code interception, PKCE bypass, open redirect chains, token leakage via referer, state parameter CSRF, token substitution, JWT confusion, implicit flow token theft, or OAuth misconfiguration in bug bounty targets. Also use when the user…
Skill Claude CodeCodex
Use when starting any pentesting engagement, receiving a target domain or IP, saying "new engagement", "start a pentest", "plan this target", or beginning any offensive security assessment. Invoke this FIRST before any other skill. Also triggers on "bug bounty on X", "test X for me", "attack X", "scope is X".
Skill Claude CodeCodex
Use when testing for race conditions, single-packet attacks, TOCTOU vulnerabilities, limit-bypass via concurrent requests, coupon/voucher reuse, double-spend, rate limit bypass, or parallel request timing attacks. Also use when the user says "race condition", "single packet attack", "concurrent requests", "double…
Skill Claude CodeCodex
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"…
Skill Claude CodeCodex
Use when running APT-level red team operations, post-exploitation, lateral movement, credential harvesting, Active Directory attacks (Kerberoasting, DCSync, Golden/Silver tickets, ADCS ESC chains, BloodHound), C2 framework tradecraft (Cobalt Strike, Havoc, Sliver), Living off the Land binaries, defense evasion (AMSI…
Skill Claude CodeCodex
Use when generating a pentest report, writing up findings from a completed assessment, converting triage output into a structured document, or producing an executive summary of vulnerabilities. Also use when the user says "generate report", "write report", or "create report".
Skill Claude CodeCodex
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, or running trufflehog/gitleaks. Also use when the user says "run secrets", "hunt secrets", or "phase 2".
Skill Claude CodeCodex
Use when aggregating pentest findings across all phases, clustering vulnerabilities by severity, prioritizing findings for a report, or surfacing the top actionable issues from a completed scan. Also use when the user says "triage", "aggregate findings", or "what did we find".
Skill Claude CodeCodex
Use when hunting for zero-days, backdoors, RCE, supply chain attacks, JWT vulnerabilities, cache poisoning, HTTP smuggling, dependency confusion, source map exposure, GSRM/WAF bypass, internal admin panel exposure, business logic flaws, race conditions, subdomain takeover, cloud misconfigs, mobile APK secrets, OAuth…