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 skills/sixoverground/claude-phases/phase-drivernpx skills add sixoverground/claude-phases --skill phase-drivergit clone --depth 1 https://github.com/sixoverground/claude-phasesWrote 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/skills/sixoverground/claude-phases/phase-driver)<a href="https://agentmods.dev/skills/sixoverground/claude-phases/phase-driver"><img src="https://agentmods.dev/badge/skills/sixoverground/claude-phases/phase-driver.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 | $0.00106 | $0.07116 |
| Opus 5 | $0.00053 | $0.03558 |
| Sonnet 5 | $0.00021 | $0.01423 |
| Haiku 4.5 | $0.00011 | $0.00712 |
Grade A, and why
phase-driver 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 5d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase driver
You execute a phased plan. The plan file is your only durable memory: the session running you can be reclaimed at any moment, and the next one starts knowing nothing. Write state down before you act on it, and everything survives.
Read references/recovery.md, references/gates.md, and references/vocabulary.md when you reach the steps that need them, not up front.
Golden rules
- Never modify the plan file from a phase branch. Plan writes go to
home_repo's plan branch, always. - Write status before the action it describes, not after. Claim before branching; record the PR before waiting on it.
- Pass the
shayou just read on every plan write. A stale sha means another driver moved: re-read, re-check whose claim it is now, and don't overwrite. - Every plan commit message ends
[skip ci]. - One phase = one PR = one repo.
- Re-read the head SHA immediately before anything irreversible and re-check the gate against it.
- If your context was compacted or you don't remember starting this: re-read this file and the plan, run Reconcile, and continue. That is the normal path, not an error.
- Never claim work you didn't do. If tests didn't run, say so in the PR body. If you can't tell why CI failed, say that and link the run.
1. Find the plan
Look for docs/plans/*.md in the current repo. More than one, and no phase named: list them and ask.
Parse the front matter under phases:. That is your entire configuration. Resolve per-repo settings by deep-merging each repo's entry over defaults. Never look for configuration anywhere else; there is no other config file.
The plan branch is plan_branch, or the home repo's default branch when that key is absent. Every read and every write of the plan file uses it. It is usually the default branch; on feature-branch work. Where phases target feature/x and nothing reaches main until the feature is whole. The plan lives there instead, so that status is visible without merging a phase PR. If plan_branch names a branch that doesn't exist, stop and say so. Never fall back to the default branch: a plan read from the wrong branch reports every phase as unstarted, and the driver would start them all a second time.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 274 lines · 106 tokens per session scan A b8d9bb70f922
phase-driver is a skill published in the GitHub repository sixoverground/claude-phases (2 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 7,116 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 skills, from other repositories
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.