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 batteryshark/rekit --skill joern-slicegit clone --depth 1 https://github.com/batteryshark/rekitWrote 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/batteryshark/rekit/joern-slice)<a href="https://agentmods.dev/skills/batteryshark/rekit/joern-slice"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/joern-slice/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/batteryshark/rekit/joern-slice"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/joern-slice.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 | $0.00049 | $0.00690 |
| Opus 5.5 | $0.00020 | $0.00276 |
| Sonnet 5.5 | $0.00010 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
joern-slice 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Joern Code Slicer
Use Joern after syntax-level inspection has identified a function, API, or behavior worth deeper analysis. It builds a code property graph (CPG), asks Joern for a bounded slice, and emits both the raw graph and a stable Rekit evidence document. This is a deeper layer than Tree-sitter, not a replacement for broad multi-language scanning.
Install
rekit install joern-slice
rekit doctor joern-slice
The explicit install step pulls the official image by immutable multi-platform digest. Analysis never pulls and always runs with Docker networking disabled.
Usage
rekit run joern-slice ./source ./out --language pythonsrc
rekit run joern-slice ./source ./out --language jssrc --mode data-flow \
--sink-filter '.*(?:eval|exec).*'
rekit run joern-slice ./source ./out --language c --mode usages
behavior-flow is the default. Its declarative profile selects source and sink
patterns without accepting executable Joern or Scala supplied by the caller. Pass a
versioned profile with --profile; its schema is in assets/profile.schema.json.
data-flow exposes Joern's bounded graph directly, while usages records method and
type usages. Use --reuse-cpg when iterating on profiles against an already generated
CPG from the same target and frontend. Reuse requires its sibling evidence.json and
verifies the target manifest, frontend, and immutable image before accepting the CPG.
Every run publishes cpg.bin, raw-slice.json, and evidence.json atomically. The
evidence records the target manifest digest, frontend, profile digest, image identity,
coverage, graph, paths, findings, resource limits, and phase timing. Joern frontends
vary: some graphs contain an explicit edge to the sink, while others end at the value
selected by the sink query. Rekit labels the latter slice-selected-by-sink; it does
not fabricate a reaching-definition edge.
Scope and safety
One run analyzes one frontend and one CPG. Mixed-language repositories require one run per relevant language; the results do not imply cross-language data flow. The default input bounds are 10,000 regular files and 512 MiB. Symlinks are excluded and reported. The target is copied into a temporary read-only mount. Target code is parsed but never executed.
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.
- 1mo ago First seen · 63 lines · 49 tokens per session scan A bb1ef6f1a0aa
joern-slice is a skill published in the GitHub repository batteryshark/rekit (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 690 once invoked, about $0.0002 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.