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 redteamgit 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/redteam)<a href="https://agentmods.dev/skills/kalpmodi/akira/redteam"><img src="https://agentmods.dev/badge/skills/kalpmodi/akira/redteam.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 5.1 | $0.00206 | $0.02848 |
| Opus 5 | $0.00103 | $0.01424 |
| Sonnet 5 | $0.00041 | $0.00570 |
| Haiku 4.5 | $0.00021 | $0.00285 |
Grade A, and why
redteam scanned grade A with 1 finding 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 8d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Linux pivot available | SUID/sudo -> cron hijack -> kernel exploits | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Team / APT Simulation Phase
Philosophy
APT simulation is not about running a tool and reporting output. It is about proving a complete kill chain - initial foothold to Crown Jewels. Every technique in this skill is used in authorized red team engagements, documented in MITRE ATT&CK, and referenced in Mandiant/CrowdStrike/Recorded Future adversary reports.
This skill activates after a foothold is established (exploit phase proved initial access) or from an assumed-breach scenario. Every technique requires written authorization scope.
Phase 0: Smart Intake
source ~/.claude/skills/_shared/phase0.sh
source ~/.claude/skills/_shared/signals.sh
p0_init_vars "$1"
p0_state_gate || exit 0
p0_read_relay exploit secrets recon cloud_audit
p0_read_memory
TECH_STACK=$(jq -r '.intel.technologies[]?' "$SESSION" 2>/dev/null | tr '\n' ',')
echo "=== REDTEAM SMART INTAKE: $TARGET ==="
echo "State: $STATE | Tech: $TECH_STACK"
echo "Confirmed vulns: $(echo "$CONFIRMED_VULNS" | grep -c .)"
echo "Internal IPs reachable: $(echo "$INTERNAL_IPS" | grep -c .)"
echo "Verified creds: $(echo "$VERIFIED_CREDS" | grep -c .)"
echo "Auth bypass confirmed: $VERIFIED_AUTH_BYPASS"
echo "ATW flagged (skip): $ATW_FLAGGED"
Intake-to-technique priority:
| Signal available | Prioritize |
|---|---|
| Internal IPs + SSRF vector | C2 setup -> lateral movement |
| AD/LDAP/Kerberos in tech stack | BloodHound -> Kerberoast -> DCSync |
| AWS keys in secrets relay | Assumed-role lateral movement -> S3/RDS |
| Azure AD hint | Device Code phishing -> Pass-the-PRT -> ADFS |
| Confirmed auth bypass | Assumed breach - skip initial access |
| Windows hosts reachable | Credential harvesting -> Pass-the-Hash |
| Linux pivot available | SUID/sudo -> cron hijack -> kernel exploits |
Phase 1: Build Execution Manifest
MANIFEST_ITEMS="[]"
[ "$VERIFIED_AUTH_BYPASS" = "false" ] && \
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt01","tool":"initial_access","priority":"MUST","status":"pending"}]')
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt02","tool":"c2_setup","priority":"MUST","status":"pending"}]')
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt03","tool":"cred_harvest","priority":"MUST","status":"pending"}]')
echo "$TECH_STACK" | grep -qi "ldap\|kerberos\|active.directory\|domain" && \
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt04","tool":"ad_attacks","priority":"MUST","status":"pending"}]')
[ -n "$INTERNAL_IPS" ] && \
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt05","tool":"lateral_movement","priority":"MUST","status":"pending"}]')
echo "$TECH_STACK" | grep -qi "aws\|azure\|gcp\|cloud" && \
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt06","tool":"cloud_apt","priority":"MUST","status":"pending"}]')
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt07","tool":"persistence","priority":"SHOULD","status":"pending"}]')
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt08","tool":"defense_evasion","priority":"SHOULD","status":"pending"}]')
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt09","tool":"data_exfil","priority":"SHOULD","status":"pending"}]')
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"rt10","tool":"opsec","priority":"IF_TIME","status":"pending"}]')
p0_manifest_write "redteam" "$MANIFEST_ITEMS"
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/ad-core.md 3.5 KB
- tech/adcs.md 3.7 KB
- tech/c2.md 3.5 KB
- tech/cloud-apt.md 5.3 KB
- tech/creds.md 3.1 KB
- tech/delegation.md 2.7 KB
- tech/evasion.md 3.9 KB
- tech/exfil.md 4.0 KB
- tech/gpo-acl.md 3.3 KB
- tech/initial-access.md 3.1 KB
- tech/lateral.md 3.1 KB
- tech/lotl.md 3.4 KB
- tech/opsec.md 4.6 KB
- tech/persistence.md 4.4 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.
- 8d ago First seen · 208 lines · 206 tokens per session scan A 68b96118120b
redteam is a skill published in the GitHub repository kalpmodi/akira (21 stars, last pushed 1mo ago), licensed MIT. It adds 206 tokens to every session and 2,848 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). 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.