agentmods.dev

address-sieve-review

address-sieve-review is a skill for Codex from DanielT777/sieve. It costs 80 tokens per session (459 once invoked), scanned A, original, MIT.

A workflow for reading and addressing code-review comments made in the Sieve VS Code extension, a tool that displays feedback beside source code.

In plain words
What is it for?
Use it to inspect the latest Sieve annotations, fix requested issues, answer questions, add relevant tests, and run focused checks.
Why use it?
It helps you find unresolved review notes and make the smallest appropriate changes without editing Sieve's own records.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 11repo changed 2d ago A scan 80 tokens original MIT

Good fit Use it to inspect the latest Sieve annotations, fix requested issues, answer questions, add relevant tests, and run focused checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielt777/sieve/address-sieve-review
View source ↗ DanielT777/sieve
Install

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.

Any agent
npx skills add DanielT777/sieve --skill address-sieve-review
Clone the repo
git clone --depth 1 https://github.com/DanielT777/sieve

Made for: Codex.

Wrote 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.

agentmods badge for address-sieve-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielt777/sieve/address-sieve-review/github.svg)](https://agentmods.dev/skills/danielt777/sieve/address-sieve-review)
Your own site
<a href="https://agentmods.dev/skills/danielt777/sieve/address-sieve-review"><img src="https://agentmods.dev/badge/skills/danielt777/sieve/address-sieve-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.

agentmods 80×15 button for address-sieve-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/danielt777/sieve/address-sieve-review"><img src="https://agentmods.dev/badge/skills/danielt777/sieve/address-sieve-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 459 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00459
Opus 5.5 $0.00032 $0.00184
Sonnet 5.5 $0.00016 $0.00092
Haiku 4.5 $0.00008 $0.00046

Measured 2d ago against content hash ab3161af82cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

address-sieve-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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/checkpoint.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/address-sieve-review/SKILL.md · 25 lines

What it actually says

Address Sieve Review

Load the review

  1. Resolve the current workspace root with git rev-parse --show-toplevel; fall back to the current directory outside Git.
  2. Search ~/.sieve/workspaces/*/workspace.json and select the entry whose workspacePath resolves to that root.
  3. Read the sibling annotations.json file. If it is absent or has no unresolved annotations, tell the user that no Sieve feedback is waiting.
  4. Treat startLine and endLine as zero-based. fileUri is the absolute target file. Missing sourceId means current working-tree changes; checkpoint (changes since the last review) also points at the file as it is now in the working tree.

Address the feedback

  1. Before the first edit, run sh scripts/checkpoint.sh <dir> from this skill's directory, where <dir> is the folder holding the annotations.json you read. Sieve then shows the user only the changes you make from here. If it fails, carry on and say so at the end.
  2. Process annotations where resolved is false, oldest first, unless the user narrows the scope.
  3. Inspect the target file and nearby code. Lines may have shifted, so verify context before editing.
  4. Make the smallest change that addresses the comment. Treat explain as a question unless a code change is clearly requested, and add tests for test annotations when applicable.
  5. Run the smallest relevant checks after editing.
  6. Apart from the checkpoint that script writes, do not edit files under ~/.sieve; Sieve remains the source of truth and the user resolves annotations there.

Finish with a compact list of annotations addressed, skipped, or needing clarification.

Files

What ships with it

2 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.

Changes

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.

  1. 2d ago Changed · +1 lines ab3161af82cf
  2. 2mo ago First seen · 24 lines · 80 tokens per session scan A 48ada68af49c

Subscribe to this mod's changes

address-sieve-review is a skill published in the GitHub repository DanielT777/sieve (11 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 459 once invoked, about $0.0003 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.

Code review
Related

address-sieve-review compared with skills from other repositories

address-sieve-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
address-sieve-reviewDanielT777/sieveSkill112d agoMITA80Codex
autoreviewopenclaw/clawhubSkill9.5kyesterdayMITA17Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA115Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermesSkill5.2kyesterdayMITA48Claude Code, Codex
revdiff-planumputun/revdiffSkill945yesterdayMITA84Claude Code
explore-unknownsdzhng/skillsSkill1.4k2d agoMITA162Claude Code, Codex
re0-mergeLilMGenius/paperthinSkill1.4k4d agoMITA70Claude Code