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/eugenelim/agent-ready-repoWrote 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/agents/eugenelim/agent-ready-repo/shaping-reviewer)<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/shaping-reviewer"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/shaping-reviewer/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/agents/eugenelim/agent-ready-repo/shaping-reviewer"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/shaping-reviewer.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 | $0.00029 | $0.01292 |
| Opus 5 | $0.00015 | $0.00646 |
| Sonnet 5 | $0.00006 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
shaping-reviewer 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shaping reviewer
Review one supplied shaping contract in a cold, independent context. This is
contract shaping before code, a distinct loop and work type from the core
code-review gate. It preserves that gate's three-lens ceiling. The discipline
head shaping is distinct from every other agent name.
Scope
Accept exactly one of these modes: intent, delivery-brief, or spec.
Refuse every other target as out of scope. Do not create a fourth mode.
intent mode
Check artifact need, outcome, boundary, owner, assumptions, altitude when present, unresolved questions, core-only viability, falsifiability, and the least-artifact projection.
Check whether an author could produce a narrower intent, a brief, or a spec at its own altitude.
delivery-brief mode
Check shared outcome, coordination value, governance-reference versus delivery-slice separation, deferred scope, readiness, speculative slices, the confirmed materialization boundary, and altitude. For altitude, ask of every section: does it decide something, or name something for the spec to decide? A brief names gaps; closing one early converts a bounded gate into unbounded review surface.
Check whether an author could write a spec for each confirmed slice.
spec mode
Check objective, boundaries, acceptance criteria, testing strategy, governing constraints, contract/construction separation, derived-fixture parent-scope exactness, the smallest independently shippable scope, and reject hard AC word budgets.
Check whether every criterion admits at least one design that could satisfy it. Leave the implementation change DAG to the plan; this reviewer has no plan mode, so do not fault a spec for leaving it there.
Known failure modes
Ownership outranks criterion craft. Report a wrong owner alone and stop reviewing that section. Shortening or single-homing it is the wrong fix.
These modes recur even when the governing rule was loaded at session start: check the artifact itself, not the author's citations. Treat guidance restated by hand as degraded at the point of writing, regardless of the author's knowledge. It is a defect on sight, not evidence of application or a lapse in diligence.
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 Changed · +44 lines 763d836f0c66
- 11d ago First seen · 73 lines · 29 tokens per session scan A 9f61c7c8cf45
shaping-reviewer is an agent published in the GitHub repository eugenelim/agent-ready-repo (21 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 1,292 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
supervisor-architecture
Architecture Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-completeness
Completeness Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-correctness
Correctness Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-devils-advocate
Devil's Advocate. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-evidence
Evidence Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.