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 mostafa-drz/claude-skills --skill build-until-agreedgit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/build-until-agreed)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/build-until-agreed"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/build-until-agreed/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/mostafa-drz/claude-skills/build-until-agreed"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/build-until-agreed.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 | $0.00209 | $0.02936 |
| Opus 5.5 | $0.00084 | $0.01174 |
| Sonnet 5.5 | $0.00042 | $0.00587 |
| Haiku 4.5 | $0.00021 | $0.00294 |
Grade A, and why
build-until-agreed 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 1mo 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Until Agreed
The builder is the worst judge of whether the work is done. This skill writes down what "done" means before building, then lets independent auditors decide — and checks their claims before acting on them.
Standing rules — they hold for the whole run, every round:
- Problem first. No contract without a named user and the pain it removes. If there isn't one, say so and stop — we don't build for the sake of building.
- Auditors are blind and read-only. Fresh, unnamed, never
fork— each round. They get the contract file, the commit range and the harness — never the ledger, the builder's reasoning, earlier findings, or each other's verdicts. The ledger is git-ignored, so no commit range can show it to them. - Nothing is fixed until it is verified. A blocking finding is a claim until a separate verifier reproduces it. Documented decisions are not defects.
- Freeze while auditing. Commit before a round; no edits until every auditor returns.
- Prefer cutting to adding. Before each fix, name what it protects. If nothing, cut.
- Never merge. Never push to the default branch. Work on a branch; the human merges.
This is enforced here, in the workflow —
Bash(git *)does not enforce it. - Explain progress. After every round, print the round block (see
reference/contract-and-ledger.md) so the user always knows where things stand and why.
Preferences
On startup, use Read to load ~/.claude/skills/build-until-agreed/preferences.md. If it
is missing, use these defaults and show the first-run intro from
reference/contract-and-ledger.md. Write the file after the first completed round.
auditors: 3 ·max-rounds: 5 ·bar:poc·review-bot:greptileoroff(asked in the contract)lenses:adopter,correctness,risk-and-simplicity(defined inreference/auditors.md)- Contract:
.build-until-agreed/<slug>.contract.mdin the target repo (committed) - Ledger:
.build-until-agreed/<slug>.ledger.mdnext to it, git-ignored by a committed.build-until-agreed/.gitignorecontaining*.ledger.md— never committed, never in a diff, never in the PR, and not a protected path (.gitand.claudewrites always prompt)
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.
- 1mo ago First seen · 202 lines · 209 tokens per session scan A 29cf86b53068
build-until-agreed is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 209 tokens to every session and 2,936 once invoked, about $0.0008 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 2026-09-16.
Other skills, from other repositories
omh-verification-gate
This is an OMH verification-gate workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
059-design-atdd
Use when reviewing whether an OpenSpec change's execution goal, acceptance criteria, and implementation or verification tasks are aligned. This should trigger for requests such as Review this OpenSpec change with ATDD; Check acceptance criteria against tasks; Find acceptance criteria without task coverage; Detect…
056-design-avoid-breaking-changes
Use when you need to review a plan, OpenSpec change, specification, or implementation proposal for breaking-change risk across commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, and release guidance. This should trigger for requests such as Review…
053-design-simple-rules
Use when Java design, refactoring, or implementation tradeoffs should be evaluated with Kent Beck's simple design rules, including passes the tests, reveals intention, has no duplication, and has the fewest elements. This should trigger for requests such as Apply simple design rules; Review this design with Beck's…