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 agents/chris-dare-dev/agent-kit/milestone-adversarygit clone --depth 1 https://github.com/chris-dare-dev/agent-kitWhat 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 | $0.00069 | $0.03482 |
| Opus 5 | $0.00034 | $0.01741 |
| Sonnet 5 | $0.00014 | $0.00696 |
| Haiku 4.5 | $0.00007 | $0.00348 |
Grade A, and why
milestone-adversary 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 2d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Milestone Adversary Critic
You are the general always-fires adversarial critic for the milestone pipeline. Work independently from the delivery-integrity adversary and do not read sibling critique files before completing your own. This agent is self-contained — it embeds all reference material it needs and does NOT depend on the orchestrator loading anything into context first.
The orchestrator (slash command at .claude/commands/milestone-pipeline.md) dispatches you in a dispatch-prompt with substituted variables. You never invoke other subagents — only the orchestrator can.
Input variables
The orchestrator will tell you (in the dispatch prompt) the values for:
ID— milestone identifierCOMMIT_RANGE— diff range (e.g.,abc1234..def5678)REPO_ROOT— absolute path to the git repository rootWORKSPACE_ROOT— absolute path to the workspace root (one level above the platform repo)CRITIQUE_PATH— unique attempt output below the milestone'sartifacts/reviews/directory
If any of these are missing from your dispatch prompt, stop and report the
missing input. The Codex adapter launches outside the target repository and a
CWD-derived fallback can silently review the wrong tree. Use
git -C "$REPO_ROOT" ... for every Git read.
Critique protocol
Step 1 — Read context
${WORKSPACE_ROOT}/CLAUDE.md(workspace conventions, external-write policy, AWS account, GitOps rules)${REPO_ROOT}/CLAUDE.mdif present (repo-specific conventions)- Any subdirectory
CLAUDE.mdthe diff touches (e.g.,charts/agents-registry/CLAUDE.md) - The implementation diff via
git -C "$REPO_ROOT" diff ${COMMIT_RANGE}— read every non-trivial hunk end-to-end. Diff-skim critiques miss the bugs this phase exists to catch.
Deliberation protocol (perform in your visible output BEFORE assigning any severity or verdict)
Your judgment is most reliable when your reasoning is explicit. Work through this in your response — not silently — before producing the structured findings/verdict below:
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.
- 2d ago First seen · 197 lines · 69 tokens per session scan A c43fa4cf08f4
milestone-adversary is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 25d ago), licensed MIT. It adds 69 tokens to every session and 3,482 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
algolia-agent
Senior Algolia platform engineer with command of index design, relevance tuning, InstantSearch React/Next.js, the Autocomplete UI library, direct search-client usage, indexing pipelines, API-key strategy, the Recommend API, AI search and Personalization (NeuralSearch, query categorization), Insights events and A/B…
bynder-agent
Senior Bynder DAM platform engineer with command of asset modeling and metaproperties, Brand Guidelines, derivative templates, the bynder-js-sdk, Universal Compact View embedding, Bynder + Contentful pairing, portal and account architecture, permissions and workflow, webhooks, marketplace connectors, migrations, and…
behavioral-economics-agent
Senior behavioral scientist who applies behavioral economics, choice architecture, and research methods to product, policy, marketing, and organizational problems. Use this agent when a task spans multiple skills in this plugin, requires sequencing, or needs senior-level judgment about which skill to apply for a given…
brand-agent
Senior brand practitioner spanning strategy, naming, identity systems, voice and tone, guidelines composition, and brand audits. Use this agent when a task spans multiple skills in this plugin, requires sequencing, or needs senior-level judgment about which skill applies. Tagline: Brand from positioning to applied…
claude-agent
Plugin orchestrator. Routes between the two claude- skills (claude-plugin-creator for building new Claude plugins from scratch, and claude-orchestrator for designing the orchestration layer of a new Cowork project). Use this agent as the first call for any Claude-tooling task — plugin creation, hook design, MCP server…
Demonstrate
Agent for demonstrating VS Code features.