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 skills add sixoverground/claude-phases --skill phase-plannergit 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-planner)<a href="https://agentmods.dev/skills/sixoverground/claude-phases/phase-planner"><img src="https://agentmods.dev/badge/skills/sixoverground/claude-phases/phase-planner.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 5.1 | $0.00085 | $0.02028 |
| Opus 5 | $0.00043 | $0.01014 |
| Sonnet 5 | $0.00017 | $0.00406 |
| Haiku 4.5 | $0.00009 | $0.00203 |
Grade A, and why
phase-planner 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 6d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase planner
You write the plan that phase-driver executes. Two jobs: break the work into phases, and capture how these repos actually work so the driver's merge gate matches reality.
Read references/detection.md for the detection procedure and references/hygiene.md for the repo checklist when you reach those steps.
The format you're writing is specified in references/format.md, and every front-matter key in references/configuration.md. Read both before you write a plan and follow them exactly; the driver's crash recovery depends on it. references/plan-template.md is an empty plan in that format; start from it rather than assembling one from memory.
1. Ask three things
Only three. Everything else you can find out yourself, and asking someone to recite their CI setup when it's sitting in the repo is a bad first impression.
- What are we building or changing? A few sentences.
- Which repos?
owner/name, possibly several. - Project name? Lowercase, hyphenated. Becomes the plan's filename.
One more thing you need but shouldn't have to ask for: home_repo, where the plan file lives and the only repo the driver writes state to. With a single repo it's that repo. With several, propose the one the work centres on. Usually the backend or the repo with the most phases, and confirm it in the same breath as your detection findings. Don't leave it unset: it's required, and a plan without it doesn't load.
2. Detect how each repo works
Never assume. Inspect, then show your evidence. See references/detection.md for what to query and what each result implies.
Report findings as a short table before writing anything:
acme/acme-web
default branch main (from the repo)
CI 2 checks on recent PRs: build, test
dispatch workflow_dispatch declared in ci.yml
reviewer Copilot reviewed the last 5 PRs
verify local (package.json, node)
Then say what you inferred, and let them correct it. People will tell you "we're moving off Copilot" or "that repo's CI is broken, ignore it", facts you cannot read from the API.
What ships with it
5 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.
- 6d ago First seen · 115 lines · 85 tokens per session scan A 244bc0b36baf
phase-planner is a skill published in the GitHub repository sixoverground/claude-phases (2 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 2,028 once invoked, about $0.0004 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…
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.
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.
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.