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 skills/phuonghx/aim-cli/red-team-tacticsnpx skills add phuonghx/aim-cli --skill red-team-tacticsgit clone --depth 1 https://github.com/phuonghx/aim-cliWrote 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/phuonghx/aim-cli/red-team-tactics)<a href="https://agentmods.dev/skills/phuonghx/aim-cli/red-team-tactics"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/red-team-tactics.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 | $0.00089 | $0.01086 |
| Opus 5 | $0.00044 | $0.00543 |
| Sonnet 5 | $0.00018 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
red-team-tactics 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 4d 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.
On **Linux**, look for SUID binaries that run as a more privileged owner, sudo rules that permit unintended commands, kernel versions with known local exploits, and cron jobs pointing at scripts you can write to. 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Team Tactics
Red teaming exists to make defenders better by safely rehearsing how a real attacker would behave. Everything below assumes written authorization, a defined scope, and an intent to report rather than to harm.
The ATT&CK lifecycle
An engagement moves through recognizable stages. They are not strictly linear -- escalation and discovery often loop -- but each has a job:
| Stage | What it accomplishes |
|---|---|
| Reconnaissance | chart the attack surface |
| Initial access | establish the first foothold |
| Execution | run code on the target |
| Persistence | survive reboots and logouts |
| Privilege escalation | reach admin or root |
| Defense evasion | stay below detection thresholds |
| Credential access | collect usable credentials |
| Discovery | learn the internal layout |
| Lateral movement | reach additional hosts |
| Collection | gather the data of interest |
| Command & control | hold a reliable channel back |
| Exfiltration / impact | remove data or demonstrate effect |
Reconnaissance
The first trade-off is passive versus active. Passive collection never touches the target -- low risk, limited yield. Active probing engages it directly -- richer data, higher chance of being noticed. Sequence accordingly: exhaust passive sources before generating traffic.
What is worth finding, and why:
| Finding | Why it matters |
|---|---|
| Technology stack | shapes which exploits are viable |
| Staff and roles | feeds social-engineering pretexts |
| IP/network ranges | bounds the scanning scope |
| Vendors and partners | opens supply-chain angles |
Gaining initial access
Choose the vector that fits the target and the rules of engagement:
| Vector | When it fits |
|---|---|
| Phishing | a human target with reachable email |
| Public exploit | an exposed, unpatched service |
| Valid credentials | leaked, reused, or cracked logins |
| Supply chain | trusted third-party access exists |
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.
- 4d ago First seen · 113 lines · 89 tokens per session scan A 8bf0be603d39
red-team-tactics is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,086 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.
implement
End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning, implementation, independent review, and PR creation. Composes spec-quality, review-quality, and schema-workflow skills into a single pipeline. Use when a user says "implement this", "work on this…
session-retrospective
Analyzes the current implementation run — evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn'…
prepare-release
End-to-end release automation — reads commits since last tag, infers semver bump, drafts changelog, creates release PR, merges it, waits for CI green, tags, and monitors the Docker build to completion. Use when the user says: prepare release, cut a release, bump version, create release PR, ship a new version, tag a…
ralph
Launcher for the Ralph-style queue drain script — emits the right node ralph-loop.mjs invocation based on the user's filter and bounds. The actual loop runs as a Node script that spawns one claude -p --worktree per iteration; this skill is the configurator, not the loop. Use when a user says: drain the backlog, ralph…
adopt-project-scope
Migrates an already-populated, unscoped Task Orchestrator database in place to the project-scoping convention — creates a project anchor root, re-parents existing work trees under it, and writes rootId back to config.yaml. Use when a user says: adopt project scope, migrate this database to project scoping, make this…