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 aahlijia/dekko --skill dekko-review-contextgit clone --depth 1 https://github.com/aahlijia/dekkoWrote 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/aahlijia/dekko/dekko-review-context)<a href="https://agentmods.dev/skills/aahlijia/dekko/dekko-review-context"><img src="https://agentmods.dev/badge/skills/aahlijia/dekko/dekko-review-context/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/aahlijia/dekko/dekko-review-context"><img src="https://agentmods.dev/badge/skills/aahlijia/dekko/dekko-review-context.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 | $0.00086 | $0.00873 |
| Opus 5 | $0.00043 | $0.00436 |
| Sonnet 5 | $0.00017 | $0.00175 |
| Haiku 4.5 | $0.00009 | $0.00087 |
Grade A, and why
dekko-review-context 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structural context before reviewing a diff
A reviewing agent that reads a diff cold misses what a call graph
already knows: what else calls the changed code, what tests should
run, and where dekko's own resolver is unsure. workset,
impacted_tests, and check_ambiguous already answer these — this
skill composes them into review context, run before the diff itself,
so the read is top-down (structure first, then lines) instead of
bottom-up.
Procedure
| Need | Use |
|---|---|
| What changed and what calls it | mcp__dekko__workset [rev] (or dekko workset [REV]) |
| What tests should run | mcp__dekko__impacted_tests [rev] (or dekko affected [REV]) |
| Where the resolver itself is unsure | mcp__dekko__check_ambiguous (or dekko equivalent) |
- Determine the diff scope. A git rev range, or the same default
workset/impacted_testsalready use: the commit the map was generated at, elseHEAD. Don't ask the user to specify this unless the default is ambiguous for the request. - Call
workset [rev]. Bundles touched-file outlines plus call-graph packs for the most central touched symbols under one token budget — this becomes the "what changed and what calls it" section of the review context. - Call
impacted_tests [rev]. Reverse call-graph reachability from the changed symbols, more reliable than grepping test files for the changed symbol's name — this becomes the "what tests should run" section. - Call
check_ambiguous. It's repo-wide, not diff-scoped, so cross-reference its top-colliding names/files against the touched symbols from step 2 yourself. Any overlap gets flagged explicitly in the review output: "dekko's resolver disclaims confidence near<file>/<name>— verify this part of the diff by hand," rather than silently trusting a clean-looking diff in a resolver-weak area. - Fold all three into the review/PR-description prompt before reading the diff line by line. Present structural context first, then read the actual diff — not appended as an afterthought.
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 First seen · 67 lines · 86 tokens per session scan A 677be22bd45f
dekko-review-context is a skill published in the GitHub repository aahlijia/dekko (3 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 873 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 2026-08-31.
Other skills, from other repositories
symbiote-impact
Trace the blast radius of a code change using Symbiote's dependency graph. This skill should be used when the user asks to "analyze impact", "what will this change break", "show affected files", "check blast radius", "impact analysis", or "what depends on this".
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.
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.
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.