semantic-recovery-campaign

semantic-recovery-campaign is a skill for Claude Code, Codex from mattmre/EVOKORE-MCP-PUBLIC. It costs 47 tokens per session (515 once invoked), scanned A, original, MIT.

A structured method for making an unfamiliar program subsystem understandable by studying its compiled code and recording supported names, types, and explanations.

In plain words
What is it for?
Use it to analyze areas such as networking, configuration, encryption, installers, or user interfaces, and to organize function renaming, type recovery, cross-reference checks, and follow-up questions.
Why use it?
It replaces scattered reverse-engineering notes with a consistent record of what is confirmed, likely, or still uncertain.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to analyze areas such as networking, configuration, encryption, installers, or user interfaces, and to organize function renaming, type recovery, cross-reference checks, and follow-up questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mattmre/evokore-mcp-public/semantic-recovery-campaign
Install

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.

Any agent
npx skills add mattmre/EVOKORE-MCP-PUBLIC --skill semantic-recovery-campaign
Clone the repo
git clone --depth 1 https://github.com/mattmre/EVOKORE-MCP-PUBLIC

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for semantic-recovery-campaign

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/semantic-recovery-campaign/github.svg)](https://agentmods.dev/skills/mattmre/evokore-mcp-public/semantic-recovery-campaign)
Your own site
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/semantic-recovery-campaign"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/semantic-recovery-campaign/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.

agentmods 80×15 button for semantic-recovery-campaign

Your own site · 80×15
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/semantic-recovery-campaign"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/semantic-recovery-campaign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00515
Opus 5 $0.00023 $0.00258
Sonnet 5 $0.00009 $0.00103
Haiku 4.5 $0.00005 $0.00052

Measured 12d ago against content hash d8cb54b3fbb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

semantic-recovery-campaign 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.

SKILLS/DEVELOPER TOOLS/semantic-recovery-campaign/SKILL.md · 63 lines

What it actually says

Semantic Recovery Campaign

Use this skill when the goal is no longer "find something interesting" but "make a subsystem understandable and durable for future analysis."

Campaign Rules

  1. Work subsystem-first, not function-random.
  2. Promote names and types only when evidence can defend them.
  3. Keep confidence levels explicit: confirmed, likely, speculative.
  4. Batch related renames and type updates so the codebase becomes more coherent with each pass.
  5. Stop and escalate to dynamic validation if the same uncertainty keeps blocking semantic cleanup.

Workflow

  1. Define the subsystem scope: networking, config, crypto, installer, UI bridge, anti-analysis, and so on.
  2. Pick representative functions and recover their real role using:
    • callers / callees
    • xrefs to and from
    • strings and constants
    • structure and API evidence
  3. Create a local glossary:
    • subsystem terms
    • recovered struct or class names
    • prefixes or naming conventions
  4. Apply durable edits:
    • function names
    • variable names
    • prototypes
    • local types
    • comments for branch purpose, not narration
  5. Record what is still blocking confidence.

Best Pairings

  • ghidra-function-analysis for each representative routine
  • ghidra-rename-and-retype for durable semantic edits
  • debugger-driven-analysis when runtime proof is required
  • orch-panel re in semantic-recovery mode for high-stakes conclusions

Deliverable Format

  • subsystem summary
  • naming glossary
  • confirmed edits
  • speculative edges
  • next proof steps
Changes

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.

  1. 12d ago First seen · 63 lines · 47 tokens per session scan A d8cb54b3fbb8

Subscribe to this mod's changes

semantic-recovery-campaign is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 515 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

ts-debug

TypeScript/Node debugging expert. Use when the user needs to debug, profile, or trace TypeScript or Node.js code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function", "why won't the process exit".

berekvolgyipeter/dotclaude · 68 tokens

py-debug

Python debugging expert. Use when the user needs to debug, profile, or trace Python code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function".

berekvolgyipeter/dotclaude · 54 tokens

wakaru

Turn minified, bundled, or transpiled JavaScript back into readable modules. Use when you encounter unreadable production JS — a webpack/esbuild/Metro/Rollup bundle, a minified vendor script, Babel/TypeScript/SWC-transpiled output, or a single mangled .js file — and need to read, audit, debug it, or recover a…

pionxzh/wakaru · 99 tokens

ctf-rev

Solve CTF reverse engineering challenges using systematic analysis to find flags, keys, or passwords. Use for crackmes, binary bombs, key validators, obfuscated code, algorithm recovery, or any challenge requiring program comprehension to extract hidden information.

cyberkaida/reverse-engineering-assistant · 52 tokens

deep-analysis

Performs focused, depth-first investigation of specific reverse engineering questions through iterative analysis and database improvement. Answers questions like "What does this function do?", "Does this use crypto?", "What's the C2 address?", "Fix types in this function". Makes incremental improvements (renaming…

cyberkaida/reverse-engineering-assistant · 98 tokens

pyghidra-scripting

Write and run Python (PyGhidra) code inside the Ghidra session that ReVa's MCP server is already attached to, using the five ReVa scripting tools — run-script, list-scripts, read-script, write-script, edit-script. Use this whenever the user asks to execute Python against the current program, reach for the Ghidra Flat…

cyberkaida/reverse-engineering-assistant · 209 tokens