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 fledgeling-co/fledgeling-plugins --skill atlas-reviewgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/atlas-review)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/atlas-review"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/atlas-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/fledgeling-co/fledgeling-plugins/atlas-review"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/atlas-review.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 | $0.00344 | $0.02312 |
| Opus 5 | $0.00172 | $0.01156 |
| Sonnet 5 | $0.00069 | $0.00462 |
| Haiku 4.5 | $0.00034 | $0.00231 |
Grade A, and why
atlas-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 3d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
atlas-review, the Atlas review conductor
You take the open pull requests on the Atlas/Bella monorepo and drive them to merged, pushed, and reported. The reporting half is not decoration: the person who opened these PRs is a non-technical product owner, and a merge they cannot read about is a merge they have to take on trust.
The sibling of atlas-publish, which starts where you finish. That skill's boundary is
"draft is where automation stops" because publishing reaches phones. Yours is different:
merging and pushing to main is recoverable, so you finish the job. What you do not do
is release.
Running as a Gemini model? Read gemini.md in this directory first, then follow this
file with the overrides it names. Other models skip it.
The loop, in the product owner's own words
Nine stages. Stages 6 to 8 are the ones nobody asks for and every stack needs.
1 review the open PRs → code-review:code-review, per PR
2 resolve what it found → YOURS. code-review reports and fixes nothing
3 commit and push
4 merge to main by REBASE → not a merge commit
5 pull → local main is now the real main
6 update the tests → cover what the PRs actually added
7 do the backend work → plus whatever the owner's notes ask for
8 test and iterate until green → unit AND automated UI, not one or the other
9 commit and push
Stage 2 exists because code-review is read-only by design. Stage 6 exists because a PR
that adds four screens adds no coverage for them. Stage 7 exists because the product owner
writes the UI and says so: "I tried not to touch anything backend/API wise and will leave
that to you." Their notes arrive as prose, not tickets, and they are a work item.
The one rule that changes what you trust
A test the diff touched is unproven until an injected fault makes it fail.
Not a style preference. Meta's TestGen-LLM deployment filtered 75% of compiling LLM-written tests as vacuous, and 30-54% of generated tests carry structural smells. Worse for you: static reading is measured Low at catching exactly the two shapes that dominate: a mock that swallows the attribute under test, and a guard over a collection that is empty. An LLM reading a test treats a mock as a valid fixture.
What ships with it
8 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.
- 3d ago First seen · 158 lines · 344 tokens per session scan A a6ae58a60d75
atlas-review is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 344 tokens to every session and 2,312 once invoked, about $0.0017 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 2026-09-09.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
pr-pending-feedback
Evaluate pending (unsubmitted) review comments on the current branch's PR and, after user confirmation, address each in a separate sub-agent and separate commit.