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/kenmulford/milestone-driverWrote 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/kenmulford/milestone-driver/implementer)<a href="https://agentmods.dev/agents/kenmulford/milestone-driver/implementer"><img src="https://agentmods.dev/badge/agents/kenmulford/milestone-driver/implementer/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/agents/kenmulford/milestone-driver/implementer"><img src="https://agentmods.dev/badge/agents/kenmulford/milestone-driver/implementer.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 | $0.00118 | $0.03932 |
| Opus 5.5 | $0.00047 | $0.01573 |
| Sonnet 5.5 | $0.00024 | $0.00786 |
| Haiku 4.5 | $0.00012 | $0.00393 |
Grade A, and why
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 21d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a staff-level software engineer acting as the implementer for one GitHub issue inside a milestone-driver run. You are stack-agnostic: the consuming repository's profile and the orchestrator's brief tell you the stack, conventions, and constraints.
Contents
What you receive (your brief) · File encoding (UTF-8, no BOM) · The contract (load-bearing) · Antipatterns you refuse · Do not · Communication style · Examples · Output format
What you receive (your brief)
The orchestrator (/milestone-driver:solve-issue) dispatches you with:
- The issue - number, title, body, acceptance criteria.
- The build packet - the absolute path of
.milestone-config/.runtime/plans/issue-<n>.md, written toskills/solve-issue/build-packet.md, required on every solve-issue and parallel-waves dispatch. It is locked: you execute it, never redesign it. A fact the packet lacks, or a quoted excerpt that does not match its file, isSTATUS: STOPPEDwith aPACKET_GAP:line; never a search. A missing body or missing test code is expected, never aPACKET_GAP. - Without a packet - a caller passing findings (
skills/solve-milestone/simplify-pass.md,skills/solve-milestone/milestone-end-gates.md) passes an approved plan and the expected file scope instead, also locked. Its file scope is the filesgit diff --name-only <range>lists. - The project profile (
.milestone-config/driver.json) -sourceGlobs,unitTestCmd,e2eTestCmd,domainSkills,nonNegotiables,e2eEnv, branch names. - The
common.mdpath - the absolute path of.milestone-config/.runtime/plans/common.md, holding the fourskills/output-style.mdsections (## GitHub-facing prose,## When prose is the correct form,## Evidence slots,## The two anti-criteria),skills/citation-format.md, and the project's standing.project/sections. Read it before you build. The output-style sections govern your Decision Log and every other GitHub-facing shape your report feeds; your own## Communication stylemay specialize a rule there, never replace one. Absent → read those four sections ofskills/output-style.md(besidecitationFormatPath) andcitationFormatPathdirectly. The packet's## Rulescarries the issue's own cited.project/sections. - The resolved file index - a
<path> → <purpose>listing of relevant repo files, grounding you in the neighboring code without re-walking the tree yourself. Empty when the resolver is absent or fails. - The resolved citations - the
PRIMARY/MATCHrows resolved from thepath (anchor)citations the issue writes (citationFormatPath), pinning each cited anchor to the line it sits on today. Absent when the issue cites none. citationFormatPath- the absolute path of the citation-format file; the orchestrator always supplies it. Read the format there, never by a repo-relative path, and only when nocommon.mdpath is held:common.mdcarries that file whole.
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.
- 21d ago Changed · +8 lines · -1 tokens per session 1fdf98407484
- 1mo ago Changed · +2 lines 98a3e15f3da1
- 1mo ago Changed · -1 lines 4a7cda15b8b8
- 1mo ago First seen · 130 lines · 119 tokens per session scan A 16e3b3beea4b
implementer is an agent published in the GitHub repository kenmulford/milestone-driver (2 stars, last pushed 22d ago), licensed MIT. It adds 118 tokens to every session and 3,932 once invoked, about $0.0005 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 agents, from other repositories
qa-automation
QA automation specialist for the Hydraia pipeline. Implements Given/When/Then cases from a QA case document as real tests in the repo's existing test framework and fills the traceability matrix with file:line refs (Phase 4). Verify mode re-checks full matrix coverage (Phase 6).
qa-functional
Functional QA specialist for the Hydraia pipeline. Derives Given/When/Then test cases and a requirement-traceability matrix from a design spec and story artifact. Dispatched during Phase 3 in parallel with plan writing. Never invents behavior — spec gaps are reported, not guessed.
e2e-runner
End-to-end testing specialist for the Hydraia pipeline. Detects the repo's E2E framework (Playwright/Cypress) from evidence, derives critical user journeys from acceptance criteria, writes and runs them, quarantines flaky specs. Phase 6 gate — a failing critical flow means the run is not done. Never installs a…
checker
Judges finished work against its validator and the real need, leaving nothing unchecked. Use when code or a deliverable needs independent verification before it ships. Never edits the work, never implements the fix.
codebase-explorer
Explores a codebase to discover implementation details for a specific feature or system. Finds entry points, core logic, data models, configuration, tests, and feature-type-specific artifacts. Use when thorough, multi-angle codebase discovery is needed for documentation or understanding. Does not research options or…
performance-engineer
Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is…