Index of every page on this site: llms.txt
All skills
sebastianelvis avatar

/rustify-probe

@814777d
Run it yourself

Capture original behavior, binary evidence, and execution traces with REA for Rustify discovery, planning, implementation, and validation. Use for controlled probes and evidence collection throughout reconstruction.

  • 6 files
  • 31.6 KB
  • Updated last week
  • GitHub
Use this Skill: https://skilld.dev/gh/sebastianelvis/rustify/rustify-probe

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈58 tokens for metadata: the name and description. ≈427 when used: this file. ≈3.2k more on demand in 3 files.

Description uses 2.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈231 characters, or 2.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Probe the original product

The agent collects evidence for a concrete reconstruction question. The agent reads .rustify/state.yaml, the caller's question, and the relevant ledger items. The agent uses the project format and the standards guide.

  1. The agent qualifies observation routes with the comparison contract before it selects inputs.
  2. The agent uses the REA method for binary inspection and runtime traces. The orchestrator owns setup and shared session coordination.
  3. The agent selects controlled inputs with the investigation method and compares the binaries.
  4. The agent preserves raw captures in .rustify/recovered/evidence/ and measured comparison reports in .rustify/verification/.
  5. The agent returns evidence records, scenario inputs, trace references, limitations, and unresolved questions to the caller.

The first probes run during characterization and discovery. Planning uses the evidence to resolve uncertain boundaries and order slices. Implementation uses the captures and mapped traces to reproduce behavior and state transitions. Validation requests fresh probes and independent challenges in addition to the existing corpus.

The agent preserves binary identities, capture paths, hashes, and REA Evidence IDs. The agent keeps provider exports in their original format. The agent records interpretations in Markdown with links to the raw evidence. The discovery skills own requirements and recovered component claims. The plan skill owns Rust correspondences and slices. The validation skill owns acceptance.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 814777d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated last week
Other metadata
metadata
{
  "dependencies": "rea",
  "rea-source": "https://github.com/morluto/rea",
  "rea-setup": "https://github.com/morluto/rea/blob/main/docs/installation.md"
}

README badge

README badge for sebastianelvis/rustify/rustify-probe