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 agentmods add instructions/kalpmodi/akira/agents-mdgit 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/instructions/kalpmodi/akira/agents-md)<a href="https://agentmods.dev/instructions/kalpmodi/akira/agents-md"><img src="https://agentmods.dev/badge/instructions/kalpmodi/akira/agents-md.svg" alt="Measured on agentmods" 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 | $0.00575 | $0.00575 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
akira AGENTS.md 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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Akira - AI Agent Adapter
Akira is an offensive security skill suite for AI agents. This file enables any AI agent to discover and use Akira's skills.
What Akira Does
Akira runs a complete pentest engagement chain:
plan-engagement -> recon -> secrets -> exploit -> zerodayhunt -> triage -> report
Plus specialized modules: 403-bypass, ad-attacks, oauth-attacks, race-conditions, cloud-audit, ctf.
Skill Index
| Skill file | Purpose |
|---|---|
skills/plan-engagement/SKILL.md |
Scope target, initialize PTT and session.json |
skills/recon/SKILL.md |
23-step recon: subdomains, AXFR, NSEC walk, passive DNS, JARM/JA4+, supply chain, reconFTW |
skills/secrets/SKILL.md |
API keys, tokens, credentials in source/JS/git |
skills/exploit/SKILL.md |
XSS, SQLi, nuclei, deserialization, SSTI, XXE |
skills/zerodayhunt/SKILL.md |
Chain attacks, JWT confusion, SSRF->cloud, WAF bypass |
skills/triage/SKILL.md |
Severity clustering, confidence scoring, FP gate |
skills/report/SKILL.md |
Pentest report or bug bounty submission |
skills/403-bypass/SKILL.md |
29+ techniques: headers, parser confusion, BreakingWAF, H2C smuggling, JWT confusion, IIS/Apache/Node specific |
skills/ad-attacks/SKILL.md |
Full Active Directory compromise chain |
skills/oauth-attacks/SKILL.md |
OAuth/OIDC exploitation |
skills/race-conditions/SKILL.md |
HTTP/2 single-packet race attacks |
skills/cloud-audit/SKILL.md |
AWS/GCP/Azure/K8s misconfigurations |
skills/ctf/SKILL.md |
CTF challenge methodology |
How to Use
To run a skill: read the skill file and follow its instructions exactly.
Example: to run recon on target.com, read skills/recon/SKILL.md and execute its steps.
Phase Artifacts
Each phase reads and writes structured files:
session.json- cross-phase intelligence (initialized by plan-engagement)interesting_<phase>.md- phase output consumed by downstream phases
Evidence Rule
Every confirmed finding must quote exact HTTP response evidence. No evidence = downgrade to potential.
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.
- 5d ago First seen · 53 lines · 575 tokens per session scan A 5ad5d76e3d4e
akira AGENTS.md is an instructions file published in the GitHub repository kalpmodi/akira (21 stars, last pushed 1mo ago), licensed MIT. It adds 575 tokens to every session, about $0.0029 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 instructions, from other repositories
pentest-ai AGENTS.md
AGENTS.md instructions for 0xSteph/pentest-ai, covering agent guide for pentest-ai, build, test, lint, types, format and layout.
web-of-flaws AGENTS.md
AGENTS.md instructions for ukorvl/web-of-flaws, covering agents guide for web of flaws, environment, workspace structure, before marking things as done and other resources.
kali-mcp CLAUDE.md
Claude Code instructions for puffert/kali-mcp, covering kali mcp pentest assistant, rules, how to report, methodology and tool quick reference.
red-run CLAUDE.md
Claude Code instructions for blacklanternsecurity/red-run, covering red-run, engagement workflow, token budget, architecture and orchestrator variants.
The-Scaffolding AGENTS.md
AGENTS.md instructions for Shad0wMazt3r/The-Scaffolding, covering bug bounty and ctf harness, rules and skills index.
The-Scaffolding CLAUDE.md
Claude Code instructions for Shad0wMazt3r/The-Scaffolding, covering bug bounty and ctf harness, rules and skills index.