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 first-tree-ai/first-tree --skill context-tree-reviewgit clone --depth 1 https://github.com/first-tree-ai/first-treeWrote 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/first-tree-ai/first-tree/context-tree-review)<a href="https://agentmods.dev/skills/first-tree-ai/first-tree/context-tree-review"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree/context-tree-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/first-tree-ai/first-tree/context-tree-review"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree/context-tree-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 502 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 491 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00089 | $0.06955 |
| Opus 5.5 | $0.00036 | $0.02782 |
| Sonnet 5.5 | $0.00018 | $0.01391 |
| Haiku 4.5 | $0.00009 | $0.00696 |
Grade A, and why
context-tree-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 1mo 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 — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Tree Review
Review the latest live state of one Context Tree pull request (PR) or merge request (MR) under the generated Context Tree Policy. A trusted server-authored run selects exactly one provider adapter:
- GitHub keeps its existing App dispatch and formal review. The App-authored PR review is the only GitHub verdict and the App credential never enters the runtime.
- GitLab uses inbound Webhook dispatch only. The Review Agent uses the host's
local
gitand exact-hostglabidentity for live reads, repair, notes, pushes and one exact-SHA squash merge. Cloud never supplies a GitLab repository credential and GitLab has no simulated approval or gate.
Both adapters share validator-first review, detached exact-head snapshots, repair-before-escalation, complete re-review after repair, and fail-closed live-binding checks.
The GitHub App webhook owns review dispatch for GitHub. GitLab inbound Webhook dispatch is separate and never grants App review authority. The App-authored PR review is the only GitHub verdict.
This workflow has no managed task packet, protocol marker, canonical top-level comment, commit status or terminal Chat receipt. Historical managed marker text has no behavior.
Authority gate
Publication and mutation require a server-authored Context Reviewer wake-up
that names provider, the repository, the PR/MR identity and trusted run
metadata and instructs the assigned reviewer to load this installed skill. Run
first-tree org context-tree review-config --json and require the live binding,
provider, enabled Reviewer and assigned Agent to match the task. A local mirror
cannot override provider authority. Reject a GitHub run for a GitLab binding,
a GitLab run for a GitHub binding, an unknown legacy provider, or any
repository/branch mismatch before clone, forge CLI use, content read or
mutation.
For GitLab, record contextReviewConnectionId and
contextReviewInstanceOrigin from the trusted run. The live config must report
providerMatchesRepository: true, the same gitlabConnection.id, and the same
exact normalized gitlabConnection.instanceOrigin. A missing connection,
changed connection id or origin, or repository-match failure invalidates the
run even when the repository path and branch are unchanged. Apply this complete
GitLab authority tuple at the initial gate and again immediately before every
repair edit, commit, push, MR note, and merge mutation.
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.
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.
- 1mo ago First seen · 610 lines · 89 tokens per session scan A f571edf89372
context-tree-review is a skill published in the GitHub repository first-tree-ai/first-tree (157 stars, last pushed 8d ago), licensed Apache-2.0. It adds 89 tokens to every session and 6,955 once invoked, about $0.0004 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
first-tree-github-scan
Agent skill for handling a single GitHub notification spawned by the First Tree github-scan daemon. Use when an agent needs to decide how to tag, comment on, escalate, or hand off a PR, issue, review request, mention, or CI event, and when it needs to choose between handling on GitHub or routing to first-tree-sync /…
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
code-review
You are a senior code reviewer. You receive diffs via stdin.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.