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.
git 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/commands/chris-dare-dev/agent-kit/milestone-pipeline)<a href="https://agentmods.dev/commands/chris-dare-dev/agent-kit/milestone-pipeline"><img src="https://agentmods.dev/badge/commands/chris-dare-dev/agent-kit/milestone-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/chris-dare-dev/agent-kit/milestone-pipeline"><img src="https://agentmods.dev/badge/commands/chris-dare-dev/agent-kit/milestone-pipeline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.10527 |
| Opus 5.5 | $0.00021 | $0.04211 |
| Sonnet 5.5 | $0.00010 | $0.02105 |
| Haiku 4.5 | $0.00005 | $0.01053 |
Grade A, and why
milestone-pipeline 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 2mo 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 — 827 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Milestone pipeline orchestrator — delivery-state v2
The main session is the sole orchestrator, state writer, findings reconciler, and owner of every human authorization boundary. Subagents never spawn other subagents, advance state, push, apply, or self-certify closure.
This pipeline separates the delivery claims:
code-complete -> published -> applied -> operationally-verified -> complete
A local commit, green check, push, rendered GitOps revision, applied workload,
and verified behavior are different facts. plan-reviewed is a mandatory
control gate, not a synonym for any delivery claim. Never collapse these facts
into one checkbox or a free-text external-write ledger.
Read before running:
data/references/pipeline-pattern-v2.mddata/references/runtime-contract.mddata/references/milestone-pipeline-state-schema.mddata/references/milestone-pipeline-artifacts-v2.mddata/references/milestone-pipeline-agent-contract.mddata/references/milestone-pipeline-critique-format.md
Arguments and scope
ID: required stable milestone id; everything before the first--.--deep: one deep researcher instead of the standard two-agent fan-out.--resume: inspect state and resume at its current phase; never replay a completed phase.
If no id was supplied, stop and ask for it. Invoke for non-trivial work with a
fixed outcome: a new module/endpoint/chart, a cross-cutting refactor, or a
delivery milestone. Do not invoke for typos, lint-only edits, simple dependency
bumps, reverts, or direct work in deploy/argocd-config-* (the initializer
refuses generated deploy repos by identity).
Required CWD for Claude is inside the target git repo. The Codex adapter runs
from the workspace root and passes an absolute --repo-root; it uses
git -C for target-repo commands. In both cases:
WS="${PERSONAL_WORKSPACE_ROOT:-$HOME/Work/workspace}"
REPO_ROOT="${REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}"
[ -d "$WS" ] || { echo "Set PERSONAL_WORKSPACE_ROOT" >&2; exit 1; }
[ -d "$REPO_ROOT" ] || { echo "Set REPO_ROOT to the target git repo" >&2; exit 1; }
STATE="$REPO_ROOT/.claude/notes/milestones/$ID/state.json"
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.
- 2mo ago First seen · 827 lines · 52 tokens per session scan A c33da08205d9
milestone-pipeline is a command published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 10,527 once invoked, about $0.0002 per session on Opus 5.5. 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 commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.