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 agentmods add skills/batteryshark/rekit/diaphora-diffnpx skills add batteryshark/rekit --skill diaphora-diffgit 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/diaphora-diff)<a href="https://agentmods.dev/skills/batteryshark/rekit/diaphora-diff"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/diaphora-diff.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.01895 |
| Opus 5 | $0.00047 | $0.00948 |
| Sonnet 5 | $0.00019 | $0.00379 |
| Haiku 4.5 | $0.00009 | $0.00189 |
Grade A, and why
diaphora-diff 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 4d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diaphora Program Diff
Match functions between two builds of a program, recover symbol names from a build that has them onto builds that don't, and emit per-function pseudocode diffs that document what actually changed.
When to use
- Name recovery — one build shipped unstripped (or you reversed it by hand); its
siblings are stripped. Match them and carry the names across. This is the highest-value
use and the reason to prefer Diaphora over
bindiff: it keeps every function's pseudocode on both sides, so a match is reviewable rather than a bare address pair. - Version lineage — a chain of releases with no source history. Diff each adjacent pair to establish what changed, when, and in which subsystem.
- Source reconstruction — recovered C++ mangled names carry
Class::methodplus parameter types, which maps binary functions back onto a source tree you're rebuilding. - Patch analysis — the changed list, sorted by ascending ratio, is the worklist.
Reach for bindiff when you want a fast structural answer or you only have Ghidra;
reach for this when match quality matters or you need the pseudocode to read.
The two halves
| Step | Needs IDA? | Cost |
|---|---|---|
export |
yes | slow — full IDA analysis, once per binary |
diff / report |
no | fast — pure Python over the exported SQLite |
Export is cached by binary hash, so a corpus of N builds costs N exports and then any pairing is cheap. Export once, diff forever.
Usage
# one-shot: export both (cached) then diff
rekit run diaphora-diff compare ./unstripped.bin ./stripped.bin ./out --decompiler
# or drive the halves yourself, sharing exports across many pairings
rekit run diaphora-diff export ./v1.01 ./cache/v1.01.sqlite --decompiler
rekit run diaphora-diff export ./v1.02 ./cache/v1.02.sqlite --decompiler
rekit run diaphora-diff diff ./cache/v1.01.sqlite ./cache/v1.02.sqlite ./out/1.01-1.02
# re-report an existing results database with different thresholds — no re-diffing
rekit run diaphora-diff report ./cache/v1.01.sqlite ./cache/v1.02.sqlite ./out \
--results ./out/results.sqlite --min-ratio 0.9
What ships with it
3 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.
- 4d ago First seen · 143 lines · 94 tokens per session scan A d401d73b31b4
diaphora-diff is a skill published in the GitHub repository batteryshark/rekit (11 stars, last pushed 25d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,895 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…