Menu

Not in the top 1,000 by GitHub stars

hermes-labs-ai/hermes-blind

Recovers the original goal of a long Claude Code or Codex session from its first user turn, so you can restate it before continuing — plus a prompt wrapper that adds evidence and hedging constraints to evaluation prompts. Deterministic, local, no model calls. Experimental.

Claude CodeCodexGemini CLIEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

claude-plugin/skills/hermes-blind/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

e40ddd2e419f → e40ddd2e419f

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → e40ddd2e419f

No earlier version was observed for comparison.

Compare on GitHub

skills/hermes-blind/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

e40ddd2e419f → e40ddd2e419f

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → e40ddd2e419f

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit e40ddd2e419ff685a8fdcf52e31e04a8c798ae0b

git clone --filter=blob:none --no-checkout https://github.com/hermes-labs-ai/hermes-blind.git .hotskills/hermes-labs-ai-hermes-blind && git -C .hotskills/hermes-labs-ai-hermes-blind checkout --detach e40ddd2e419ff685a8fdcf52e31e04a8c798ae0b # Copy each selected skill directory from .hotskills/hermes-labs-ai-hermes-blind into .claude/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/hermes-labs-ai/hermes-blind.git .hotskills/hermes-labs-ai-hermes-blind && git -C .hotskills/hermes-labs-ai-hermes-blind checkout --detach e40ddd2e419ff685a8fdcf52e31e04a8c798ae0b # Copy each selected skill directory from .hotskills/hermes-labs-ai-hermes-blind into .agents/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/hermes-labs-ai/hermes-blind.git .hotskills/hermes-labs-ai-hermes-blind && git -C .hotskills/hermes-labs-ai-hermes-blind checkout --detach e40ddd2e419ff685a8fdcf52e31e04a8c798ae0b # Copy each selected skill directory from .hotskills/hermes-labs-ai-hermes-blind into .gemini/skills/<skill-name>/
10GitHub stars
0stars in 7 days
2skills in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 202610

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

hermes-blind

When your agent uses it

Recover the original goal of a long Claude Code or Codex session using the hermes-blind CLI. Trigger when the user asks what the original goal or ask was, wants the session re-anchored, or a long session seems to have drifted from its first turn.

What it loads into context

Frontmatter

65 tokens

Always available to the agent

SKILL.md

763 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

    Files

    • ../../../.claude-plugin/marketplace.jsonasset599 bytes
    • ../../../.claude-plugin/plugin.jsonasset385 bytes
    • ../../.claude-plugin/plugin.jsonasset385 bytes
    • SKILL.mdcore2,906 bytes
    Read SKILL.md
    
Hermes Blind reads the first user turn from this session's local JSONL log
and writes a compact, inspectable recovery anchor. It is deterministic,
makes no model calls, and sends no network requests
(https://github.com/hermes-labs-ai/hermes-blind).

1. Pick a runner: if `hermes-blind --help` works, use the bare `hermes-blind`
   command below. Otherwise prefer `uvx hermes-blind==0.3.2` (zero-install,
   no PATH changes) over `pipx install hermes-blind==0.3.2` unless the user
   wants it installed persistently. Keep the exact version pin on either so
   neither fetches an unreviewed newer release. Keep using whichever runner
   you picked for the rest of these steps — `uvx hermes-blind==0.3.2 --help`
   alone does not put `hermes-blind` on PATH.
2. Run from the session's working directory, substituting the current turn
   number and the runner from step 1 (`hermes-blind ...` or
    View the complete source on GitHub

    Skills included

    • hermes-blind
    • hermes-blind

    Repository facts

    License
    Apache-2.0
    Created
    Apr 24, 2026
    Last pushed
    Oct 2, 2026
    Forks
    2
    Open issues
    1
    Project activity
    Active

    Before you install

    Network or broad shell

    Automated signals, not a guarantee

    Checked Nov 6, 2026

    Show all 20 signals by file

    .claude-plugin/marketplace.json

    • Network accessline 1
      {   "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
    • Network accessline 2
      "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
    • Network accessline 6
      "name": "Hermes Labs",     "email": "roli@hermes-labs.ai",     "url": "https://github.com/hermes-labs-ai"
    • Network accessline 7
      "email": "roli@hermes-labs.ai",     "url": "https://github.com/hermes-labs-ai"   },
    • Network accessline 8
      "url": "https://github.com/hermes-labs-ai"
    • Network accessline 14
      "description": "Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts",       "category": "productivity",       "homepage": "https://hermes-labs.ai/open-source"
    • Network accessline 15
      "category": "productivity",       "homepage": "https://hermes-labs.ai/open-source"     }
    • Network accessline 16
      "homepage": "https://hermes-labs.ai/open-source"

    .claude-plugin/plugin.json

    • Network accessline 4
      "description": "Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts",   "author": { "name": "Hermes Labs", "email": "roli@hermes-labs.ai" },   "homepage": "https://hermes-labs.ai/open-source",
    • Network accessline 5
      "author": { "name": "Hermes Labs", "email": "roli@hermes-labs.ai" },   "homepage": "https://hermes-labs.ai/open-source",   "repository": "https://github.com/hermes-labs-ai/hermes-blind",
    • Network accessline 6
      "homepage": "https://hermes-labs.ai/open-source",
    • Network accessline 7
      "repository": "https://github.com/hermes-labs-ai/hermes-blind",

    claude-plugin/.claude-plugin/plugin.json

    • Network accessline 4
      "description": "Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts",   "author": { "name": "Hermes Labs", "email": "roli@hermes-labs.ai" },   "homepage": "https://hermes-labs.ai/open-source",
    • Network accessline 5
      "author": { "name": "Hermes Labs", "email": "roli@hermes-labs.ai" },   "homepage": "https://hermes-labs.ai/open-source",   "repository": "https://github.com/hermes-labs-ai/hermes-blind",
    • Network accessline 6
      "homepage": "https://hermes-labs.ai/open-source",
    • Network accessline 7
      "repository": "https://github.com/hermes-labs-ai/hermes-blind",

    claude-plugin/skills/hermes-blind/SKILL.md

    • Network accessline 7
      and writes a compact, inspectable recovery anchor. It is deterministic, makes no model calls, and sends no network requests (https://github.com/hermes-labs-ai/hermes-blind).
    • Network accessline 9
      (https://github.com/hermes-labs-ai/hermes-blind).

    skills/hermes-blind/SKILL.md

    • Network accessline 7
      and writes a compact, inspectable recovery anchor. It is deterministic, makes no model calls, and sends no network requests (https://github.com/hermes-labs-ai/hermes-blind).
    • Network accessline 9
      (https://github.com/hermes-labs-ai/hermes-blind).

    How the signals fit together

    Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

    Some files could not be read; the facts below still hold.

    Signal confidence: 4 facts

    Works with

    Agent compatibility, from the files in this repository
    AgentStatusEvidenceInstall to
    Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
    CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
    CursorCompatibleStandard SKILL.md claude-plugin/skills/hermes-blind/SKILL.md.cursor/skills/<skill-name>/
    Gemini CLINativeManifest gemini-extension.json.gemini/skills/<skill-name>/
    GitHub CopilotCompatibleStandard SKILL.md claude-plugin/skills/hermes-blind/SKILL.md.github/skills/<skill-name>/
    OpenCodeCompatibleStandard SKILL.md claude-plugin/skills/hermes-blind/SKILL.md.opencode/skills/<skill-name>/
    • Native The repository ships a manifest, folder or frontmatter field for this agent.
    • Compatible A standard SKILL.md that this agent can read.
    • Unknown No evidence either way.

    Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

    You might also use

    wanshuiyin/HERO-Anti-OverDefense

    HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, …

    798GitHub stars

    NousResearch/hermes-agent

    The agent that grows with you

    261.3kGitHub stars

    DietrichGebert/ponytail

    Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

    186kGitHub stars

    KKKKhazix/khazix-skills

    数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

    22kGitHub stars

    0xNyk/council-of-high-intelligence

    Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.

    4.8kGitHub stars

    NVIDIA/skills

    Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

    3.9kGitHub stars