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/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/plan-master)<a href="https://agentmods.dev/commands/oborchers/fractional-cto/plan-master"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-master/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/oborchers/fractional-cto/plan-master"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-master.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 | $0.00044 | $0.02224 |
| Opus 5.5 | $0.00018 | $0.00890 |
| Sonnet 5.5 | $0.00009 | $0.00445 |
| Haiku 4.5 | $0.00004 | $0.00222 |
Grade A, and why
plan-master 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are drafting a master planning document. The output is a project-local .md file in the user's repository, written by the plan-master-architect agent following the master-plan-methodology skill.
Input: $ARGUMENTS
Parse the arguments:
- Topic (required) — a ticket ID, ticket URL, file path, or free-form scope statement.
--context <path>(optional) — path to a scratch directory from a prior/planning-tools:plan-contextrun (containing per-domain worker findings). If supplied, skip the discovery pre-flight and go straight to synthesis.--domains a,b,c(optional) — use this domain partition verbatim instead of the Triage partition.--out <path>(optional) — write the plan to this file or directory instead of the auto-resolved location.
If arguments are empty, ask the user for a topic via AskUserQuestion before proceeding.
Ticket-source detection (Step 0)
Before treating the topic as free-text, run pattern detection against the first argument. If it matches one of these forms, fetch the ticket source via the adapter contract codified in planning-tools:progress-methodology:
| Pattern | Provider |
|---|---|
^[A-Z]{2,6}-\d+$ (e.g., AIA-1234, CI-21) |
Linear |
^https://linear\.app/.+/issue/([A-Z]{2,6}-\d+)/ |
Linear |
^https://github\.com/([^/]+)/([^/]+)/(issues|pull)/(\d+) |
GitHub |
^([^/\s]+/[^/\s]+)#(\d+)$ (e.g., org/repo#42) |
GitHub |
On a match:
- Fetch title, body, and all comments (no cap, per the comment-fetch policy in
progress-methodology):- Linear:
mcp__linear-server__get_issue(id)+mcp__linear-server__list_comments(issueId). - GitHub:
gh issue view <N> --repo <owner>/<repo> --json title,body,state,url,comments(orgh pr view).
- Linear:
- Treat the fetched
{ title, body, comments[] }as additional source artifact context for Stage 1 Triage and propagate it to Stage 3 workers + the architect. The Triage step scans comments for: acceptance criteria, prior decisions, unresolved questions to surface as Open Questions, and recent reroutes that override the body. - Save the ticket URL on the architect's input so the rendered plan includes a
- **Ticket:** <url>bullet as the first context bullet (per themaster-plan-methodologyskill).
If the matched provider's MCP/CLI is unavailable, fail loudly: e.g., Linear MCP not loaded — cannot fetch <ticket>. Re-run on a session that has the Linear MCP, or pass the topic as free-form text. Do not silently degrade.
If no pattern matches → existing free-text behavior (no fetch, no - **Ticket:** bullet).
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 · 135 lines · 44 tokens per session scan A f0949b272fd2
plan-master is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 2,224 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 2026-10-13.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.