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 agentmods add skills/e0ipso/strikethroo/st-code-reviewnpx skills add e0ipso/strikethroo --skill st-code-reviewgit clone --depth 1 https://github.com/e0ipso/strikethrooWrote 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/e0ipso/strikethroo/st-code-review)<a href="https://agentmods.dev/skills/e0ipso/strikethroo/st-code-review"><img src="https://agentmods.dev/badge/skills/e0ipso/strikethroo/st-code-review.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 | $0.00087 | $0.01444 |
| Opus 5 | $0.00044 | $0.00722 |
| Sonnet 5 | $0.00017 | $0.00289 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
st-code-review 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 today.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
st-code-review
Review a Strikethroo plan's cumulative diff as an independent reviewer, running on a different harness than the one that wrote the code. <root> is the workspace root the dispatch supplies.
Your findings are recorded, not applied. The implementer reads them and decides what to act on, so write each one to be judged on its evidence rather than to survive a filter.
Grading
Grade severity and confidence per <root>/config/hooks/CODE_REVIEW.md, which is authoritative.
Anti-rationalization
Read <root>/config/shared/anti-rationalization.md. Every row below is an excuse you will be tempted to make.
| You catch yourself thinking... | The binding rule |
|---|---|
| "This could theoretically fail if..." | Name the concrete input or state, or it is not a finding. |
| "The plan does not say this, but it should have." | You check conformance to what the plan states, not to what it ought to have stated. |
| "This works, but the abstraction is wrong." | Design opinion. Record nothing. |
| "I am unsure, so I will justify at length to be safe." | Length is not evidence. Lower confidence instead. |
| "The caller probably handles this." / "...probably does not." | An unread caller is an assumption. Read it, or mark confidence="medium" and state the assumption in the body. |
"Only minor, but real, so I will call it major so someone acts on it." |
Severity is impact. Inflating it corrupts the one signal the reader sorts by. |
| "I found nothing, so I should look harder until this produces something." | A clean diff is a valid result. Manufacturing findings to justify the run is the defect this gate exists to stop. |
Output
Emit one document in the urn:self-review:v2 namespace. It must validate against <root>/config/schemas/self-review-v2.xsd. Give every changed file its own <file> element, including the files you read and had no comment on. path is repository-relative. change-type is added, modified, deleted, or renamed. Give each comment exactly one line pair: new-line-* for added or context lines, old-line-* for deleted ones, both absent for a file-level comment, start equal to end for a single line. Read references/review-example.xml.md before emitting; it shows a complete valid document with one commented file and one clean file.
What ships with it
4 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.
- today Changed · -34 lines b687c4ef8e58
- 5d ago First seen · 91 lines · 87 tokens per session scan A 73808a67afe2
st-code-review is a skill published in the GitHub repository e0ipso/strikethroo (48 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,444 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 2026-08-30.
Other skills, from other repositories
business-requirements
Read and hand-edit the app's business requirements — the checklist the harness verifies the built app against. MUST be loaded whenever the user asks to add, change, remove, reword, re-prioritise, or reclassify a business requirement (e.g. "add a requirement that…", "that rule is wrong, fix it", "drop the requirement…
first-run-open
Owns the opening move of first-run when the user has NOT handed you a substantive prompt (cold start), and sets the voice-vs-text opening posture for any open. Shows a provisional dream and a guess about who the user is, then learns from their correction (show-to-learn) and re-aims. Hands back to the first-run spine…
disqualification
The honest exit. Loads when qualification signals sustained-low or a realism failure (the ask is genuinely outside QB's wheelhouse). Acknowledges the mismatch plainly, suggests a realistic alternative, preserves dignity, and does not chase. A legitimate designed outcome, not a framework failure.
qualification
Reads qualification signals from the user's input and passive context, sets the archetype and effort mode, and decides whether to proceed up the convince ladder or route to the disqualification skill. Runs alongside the first-run spine from the first substantive message onward. Falls back to "proceed at normal effort"…
build-recovery
Owns the build wait and build failure. Narrates the generation honestly while it runs, and when it errors, names the failure plainly with a real recovery path instead of a generic "oops". Loads when generation is long or returns an error. The single highest-risk moment for the "it's actually building" belief.
chat-formatting-widgets
Governs the custom markdown widgets rendered in the QuantumByte chat interface. This includes the inline highlight-mark span (use on every question the user must answer). You must check this skill on every reply to format highlights.