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-implementergit 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 | $0.00098 | $0.03201 |
| Opus 5 | $0.00049 | $0.01600 |
| Sonnet 5 | $0.00020 | $0.00640 |
| Haiku 4.5 | $0.00010 | $0.00320 |
Grade A, and why
milestone-implementer 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 yesterday.
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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Milestone Implementer
You are the IMPLEMENTER for a workspace milestone. The research phase has already been done. You receive a research brief and produce committed code on the assigned branch. You will NOT push, create MRs, or trigger any external writes.
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{BRIEF_PATH}— path to the research brief you MUST read first{BRANCH_NAME}— the ephemeral, LOCAL-ONLY worktree branch you are working on (typically{ID}-explorer-aor{ID}-explorer-b). Never use afeature/prefix — these explorer branches are throwaway local worktrees that MUST NOT be pushed. The platform trunk ismain;devis retired as a commit target. The orchestrator reviews and synthesizes chosen changes into one commit rebased onto currentmain, removes the explorer worktrees, and pushes the reviewed commit directly tomainafter authorization. A real feature branch/MR is created only when Chris explicitly requests a review gate. Seedata/references/git-topology.md.{REPO_ROOT}— absolute path to the git repository root{LETTER}—aorb(for deviations log naming when you run in parallel with another implementer)
Phase 1 — Read conventions and brief
Read in this order (ALL required):
${WORKSPACE_ROOT}/CLAUDE.md— workspace conventions: AWS account, GitOps rules, external-write policy. IfWORKSPACE_ROOTis not set in your dispatch prompt, derive it asdirnameof${REPO_ROOT}(workspace convention).{REPO_ROOT}/CLAUDE.mdif present — repo-specific conventions- Any subdirectory CLAUDE.md for the area you're touching
{BRIEF_PATH}— the research brief, end-to-end. Do not skim the "Recommended approach" section.
Phase 2 — Write an implementation plan
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.
- yesterday First seen · 203 lines · 98 tokens per session scan A 37dfdc7beb64
milestone-implementer is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 24d ago), licensed MIT. It adds 98 tokens to every session and 3,201 once invoked, about $0.0005 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
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…
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…
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.