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 IsaiaScope/ai --skill iso-writegit clone --depth 1 https://github.com/IsaiaScope/aiWrote 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/isaiascope/ai/iso-write)<a href="https://agentmods.dev/skills/isaiascope/ai/iso-write"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-write/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/skills/isaiascope/ai/iso-write"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-write.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 | $0.00172 | $0.03123 |
| Opus 5.5 | $0.00069 | $0.01249 |
| Sonnet 5.5 | $0.00034 | $0.00625 |
| Haiku 4.5 | $0.00017 | $0.00312 |
Grade A, and why
iso-write 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 27d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iso-write
Execute a Claude/Codex-authored plan using TDD in the workspace mode the user picks. Never commit. Leave every change in the working tree so the user reviews the full diff at the end of the writing session and commits manually.
Input
Invoked as /iso-write <plan_path> [workspace-flag] — <plan_path> is the path to the plan markdown file (e.g. docs/superpowers/plans/2026-05-26-feat-thing.md).
An optional workspace flag selects where the implementation happens. The flags are mutually exclusive:
| Flag | Workspace |
|---|---|
| (none) | Reuse, resume, or cut — on a base branch (dev, develop, test, prod, main, master) or detached HEAD, derive <type>/<slug> from the plan filename: check it out if it exists, create it if not. Already on a feature branch: stay on it, create nothing. |
--no-branch |
In place — stay on the current branch, no checkout. |
--branch=<name> |
Named branch — checkout <name>, creating it if missing. |
--worktree |
Worktree — isolated worktree on a fresh <type>/<slug> branch via the using-git-worktrees skill. |
If <plan_path> is missing or the file does not exist, halt:
iso-write: plan not found: <plan_path>.
If more than one workspace flag is given, halt:
iso-write: pick one workspace mode.
Pre-flight
# scripts/write.sh resolve refuses on all three: no git, no repo, no plan.
eval "$(scripts/write.sh resolve "$plan_path" $workspace_flag)"
# $mode and $branch are now set
A dirty working tree (staged or unstaged) is not refused. How Step 2 handles it depends on the mode: the default and --branch=<name> modes stash the changes and carry them onto the target branch; --no-branch leaves them in place; --worktree leaves them in the main checkout (the worktree starts clean).
Never create a worktree the user did not ask for. --worktree is the only
way this skill ends up in one — not a fallback, not a workaround for a busy
checkout, and never for a second repo a plan touches. Iso does not want
worktrees: a sibling directory holding half the change is one more place to
review, and it moves core.hooksPath and other shared config under the main
checkout anyway.
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.
- 27d ago Changed · +16 lines 1a2d97881089
- 1mo ago First seen · 207 lines · 172 tokens per session scan A 6e94d3908205
iso-write is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed 7d ago), licensed MIT. It adds 172 tokens to every session and 3,123 once invoked, about $0.0007 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 skills, from other repositories
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
rust-tdd
Use when implementing Rust features test-first, reproducing Rust bugs with regression tests, characterizing legacy Rust, or applying red-green-refactor with cargo test. Covers boundary and equivalence cases, proptest shrinking, mockall expectations, rstest fixtures, async/concurrent/CLI tests, and coverage…
agent-evaluation
Use when testing skills, commands, or agents for quality. Use after creating new skills, before deploying agents, or when debugging inconsistent agent behavior. Triggers on "evaluate", "test quality", "is this skill working", or QA of AI workflows.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
test-driven-development
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality. Use when asked to add tests to a function, fix a bug…