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 tdwhere123/do-it --skill do-it-reviewgit clone --depth 1 https://github.com/tdwhere123/do-itWrote 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/tdwhere123/do-it/do-it-review)<a href="https://agentmods.dev/skills/tdwhere123/do-it/do-it-review"><img src="https://agentmods.dev/badge/skills/tdwhere123/do-it/do-it-review/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/tdwhere123/do-it/do-it-review"><img src="https://agentmods.dev/badge/skills/tdwhere123/do-it/do-it-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.00405 |
| Opus 5.5 | $0.00009 | $0.00162 |
| Sonnet 5.5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
do-it-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 12d 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.
What it actually says
Review
Keep two lenses distinct: Spec asks whether the implementation satisfies the user's requirements, settled decisions, boundaries, and acceptance; Standards asks whether its ownership, contracts, failure behavior, and maintainability are sound. Passing either lens does not close a failure in the other.
Inspect the actual diff, callers, and relevant evidence. An independent context is valuable when the author or parent may be anchored: give the reviewer the goal, scope, decisions, and source facts, not an authoritative parent verdict. Let the reviewer gather evidence and reach their own conclusion.
Collect the complete finding batch before causal repairs when findings may share a root. Cluster related failures, repair the rightful owner, and check the repair's affected surface. Re-review depth follows new changes, remaining doubt, and risk; no fixed number of reviewers or repair rounds applies.
For explicit deep audits, Audit governs file, layer, and chain coverage and fresh causal synthesis before repair proposals. Ordinary reviews do not inherit that workflow.
A useful finding identifies its location, consequence, evidence, and needed correction (deferred until synthesis during an audit), and changes a decision; seek refuting evidence before reporting, and leave out style preference and unreachable hypotheticals. Distinguish blocking defects, important regressions, and optional improvements. Do not claim clean while material findings remain unresolved; identify anything not checked or deliberately deferred. Use the user's review vocabulary when one is specified.
Review lenses provide optional specialist detail; for example, use the maintainability lens when an added abstraction, export, dependency, or parallel implementation raises a concrete necessity or change-cost question. Keep that inspection bounded to the change and affected contracts.
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.
- 12d ago Changed · +2 lines 60e882a93022
- 16d ago Changed · +8 lines 7538d14eb952
- 1mo ago Changed · -66 lines · -12 tokens per session c7e8b5877ef3
- 1mo ago Changed · +23 lines 51c33ed0e42b
- 1mo ago First seen · 73 lines · 34 tokens per session scan A 327ae244b2a4
do-it-review is a skill published in the GitHub repository tdwhere123/do-it (28 stars, last pushed 12d ago), licensed MIT. It adds 22 tokens to every session and 405 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
code-reviewer
Automatic code quality and best practices analysis. Use proactively when files are modified, saved, or committed. Analyzes code style, patterns, potential bugs, and security basics. Triggers on file changes, git diff, code edits, quality mentions.
dpf-architecture-review
Use when reviewing or updating a DPF spec, design doc, or implementation plan for architectural alignment.
review-arch
Conduct a principal-level architecture review of a system, specification, diagram, or set of design decisions. Use when asked to review an architecture, evaluate a design, assess coupling/cohesion, check for anti-patterns, audit system boundaries, or produce an Architecture Review Board (ARB) style verdict. Also use…
review-impl
Review implementation changes for a given task against architectural standards. Use when reviewing a PR, evaluating recently committed code, assessing whether implementation changes are correct and architecturally sound, or when asked to 'review my changes', 'check this implementation', 'review what I built', 'is this…
dpf-blast-radius
Use before shipping a DPF change to find what it breaks elsewhere — a refactor, renamed field, contract/schema/enum edit, shared helper, or a diff you do not trust.
committed-change-semantic-review
Review a committed change before publication.