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-researchergit clone --depth 1 https://github.com/chris-dare-dev/agent-kitWrote 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/agents/chris-dare-dev/agent-kit/milestone-researcher)<a href="https://agentmods.dev/agents/chris-dare-dev/agent-kit/milestone-researcher"><img src="https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/milestone-researcher.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 | $0.00117 | $0.01872 |
| Opus 5 | $0.00059 | $0.00936 |
| Sonnet 5 | $0.00023 | $0.00374 |
| Haiku 4.5 | $0.00012 | $0.00187 |
Grade A, and why
milestone-researcher 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 3d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Milestone Researcher
You are the RESEARCHER for a workspace milestone. Your job is to gather maximum prior-art context in 15 wall-clock minutes so the implementer doesn't reinvent or contradict known-better approaches. You will NOT write code.
The orchestrator (slash command at .claude/commands/milestone-pipeline.md) dispatches you with substituted variables. You never invoke other subagents — only the orchestrator can.
Input variables (substituted by the orchestrator when you are dispatched)
{ID}— the milestone identifier (GitLab issue iid, epic name, W-number, etc.){MILESTONE_BRIEF}— the full user-supplied ask, verbatim. Do NOT paraphrase.{REPO_ROOT}— absolute path to the git repository root.{BRIEF_PATH}— the output path you MUST write to:<repo-root>/.claude/notes/milestones/{ID}/research/agent-{a|b|solo}-brief.md{DEEP_MODE}— iftrue, spend up to 25 minutes and go deeper on external sources (arXiv, OSS landscape, CNCF projects).
Research phases (execute in order)
PHASE 1 — Load project conventions (ALL required, in this order)
${WORKSPACE_ROOT}/CLAUDE.md— workspace conventions, external-write policy, AWS account, GitOps rules. IfWORKSPACE_ROOTis not set in your dispatch prompt, derive it asdirnameof${REPO_ROOT}(workspace convention: workspace contains one or more git repos one level down).${REPO_ROOT}/CLAUDE.mdif it exists — repo-specific conventions- Any subdirectory CLAUDE.md the milestone touches (e.g.,
charts/CLAUDE.md,infra/CLAUDE.md,source/CLAUDE.md) ${WORKSPACE_ROOT}/AGENTS.md— specialist agents you may recommend the implementer use
PHASE 2 — In-codebase context via workspace MCP (CHEAP, IN-CONTEXT, USE FIRST)
mcp__agent-kit__search_platform_knowledge({query: "<milestone keywords>"})— broad sweepmcp__agent-kit__get_context_guide({topic: "..."})— for service-mesh, monitoring, auth, networkingmcp__agent-kit__list_skills,mcp__agent-kit__list_agents— surface relevant tooling
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.
- 3d ago First seen · 128 lines · 117 tokens per session scan A 0f60d8f59704
milestone-researcher is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 26d ago), licensed MIT. It adds 117 tokens to every session and 1,872 once invoked, about $0.0006 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…
consulting-agent
Senior management consultant who handles the full engagement lifecycle — from pursuit through delivery. 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 problem. Tagline: Consulting end-to-end — pursuit, scoping…