Not in the top 1,000 by GitHub stars
lorem-dev/duolog
duolog makes Claude Code and Codex work as a pair in one project. You choose which agent and model does each kind of work. The two sessions then talk through a cheap file bus, so they do not paste large context at each other.
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
plugin/claude/skills/duolog/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 19897f4e85b9
No earlier version was observed for comparison.
plugin/codex/skills/duolog/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 19897f4e85b9
No earlier version was observed for comparison.
Verified commit 19897f4e85b975ca5338e2b1f41dd3139afb3700
git clone --filter=blob:none --no-checkout https://github.com/lorem-dev/duolog.git .hotskills/lorem-dev-duolog && git -C .hotskills/lorem-dev-duolog checkout --detach 19897f4e85b975ca5338e2b1f41dd3139afb3700
# Copy each selected skill directory from .hotskills/lorem-dev-duolog into .claude/skills/<skill-name>/Heat
Insufficient historyNot enough history yet to measure heat. It appears after a few days of data.
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
duolog
When your agent uses it
Delegate a bounded task to a second Claude or Codex session with duolog and read its short answer. Use for self-contained work or a second opinion.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
693 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before you start
- Hand over
- When duolog says `run here`
- Permission requests
- Live sessions
- Never
Files
../../../../.claude-plugin/marketplace.jsonasset348 bytes../../.claude-plugin/icon.pngasset24,893 bytes../../.claude-plugin/icon.svgasset5,562 bytes../../.claude-plugin/plugin.jsonasset457 bytes../../hooks/hooks.jsonasset2,217 bytesSKILL.mdcore2,604 bytesSKILL.mdcore2,604 bytesSKILL.mdcore2,604 bytes
Read SKILL.md
# duolog
## Before you start
1. Run `duolog version`. If it is not found, tell the user and offer the
command for this OS below. Run it only if they agree.
macOS/Linux:
```sh
curl -fsSL https://github.com/lorem-dev/duolog/releases/download/v1.0.0/install.sh | sh -s -- --version v1.0.0 && duolog install --scope project
```
Windows PowerShell:View the complete source on GitHubduolog
When your agent uses it
Delegate a bounded task to a second Claude or Codex session with duolog and read its short answer. Use for self-contained work or a second opinion.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
693 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before you start
- Hand over
- Running from Codex
- When duolog says `run here`
- Permission requests
- Live sessions
- Never
Files
SKILL.mdcore2,648 bytesSKILL.mdcore2,648 bytesSKILL.mdcore2,648 bytes
Read SKILL.md
# duolog
## Before you start
1. Run `duolog version`. If it is not found, tell the user and offer the
command for this OS below. Run it only if they agree.
macOS/Linux:
```sh
curl -fsSL https://github.com/lorem-dev/duolog/releases/download/v1.0.0/install.sh | sh -s -- --version v1.0.0 && duolog install --scope project
```
Windows PowerShell:View the complete source on GitHubSkills included
- duolog
- duolog
Repository facts
- License
- Apache-2.0
- Created
- Oct 31, 2026
- Last pushed
- Nov 6, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 4 notes
plugin/claude/skills/duolog/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugin/claude/skills/duolog/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugin/codex/skills/duolog/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugin/codex/skills/duolog/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 2 dangerous shell commandsin 2 files: duolog/SKILL.md:19 duolog/SKILL.md:18
- 14 network referencesin 5 files: plugin/claude/.claude-plugin/plugin.json:5 .claude-plugin/marketplace.json:4 duolog/SKILL.md:19 and 2 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 1 reference to secretsin 1 file: duolog/SKILL.md:46
- No requests to vote in Hot
Show all 17 signals by file
.claude-plugin/marketplace.json
plugin/claude/.claude-plugin/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1024 1024" width="1024" height="1024">
plugin/claude/.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Lorem Dev", "url": "https://github.com/lorem-dev" - Network accessline 6
"name": "Lorem Dev", "url": "https://github.com/lorem-dev" }, - Network accessline 7
"url": "https://github.com/lorem-dev" - Network accessline 8
}, "homepage": "https://github.com/lorem-dev/duolog", "repository": "https://github.com/lorem-dev/duolog", - Network accessline 9
"homepage": "https://github.com/lorem-dev/duolog", - Network accessline 10
"repository": "https://github.com/lorem-dev/duolog",
plugin/claude/skills/duolog/SKILL.md
- Dangerous shell operationline 19
curl -fsSL https://github.com/lorem-dev/duolog/releases/download/v1.0.0/install.sh | sh -s -- --version v1.0.0 && duolog install --scope project - Network accessline 19
curl -fsSL https://github.com/lorem-dev/duolog/releases/download/v1.0.0/install.sh | sh -s -- --version v1.0.0 && duolog install --scope project - Network accessline 25
$env:DUOLOG_VERSION = 'v1.0.0'; irm https://github.com/lorem-dev/duolog/releases/download/v1.0.0/install.ps1 | iex
plugin/codex/skills/duolog/SKILL.md
- Dangerous shell operationline 18
curl -fsSL https://github.com/lorem-dev/duolog/releases/download/v1.0.0/install.sh | sh -s -- --version v1.0.0 && duolog install --scope project - Network accessline 18
curl -fsSL https://github.com/lorem-dev/duolog/releases/download/v1.0.0/install.sh | sh -s -- --version v1.0.0 && duolog install --scope project - Network accessline 24
$env:DUOLOG_VERSION = 'v1.0.0'; irm https://github.com/lorem-dev/duolog/releases/download/v1.0.0/install.ps1 | iex - Access to secretsline 46
[Credential-related source omitted]
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.
Combined signals: 2 facts
- Passes content downloaded from github.com to an interpreterduolog/SKILL.md:19High confidence
- Passes content downloaded from github.com to an interpreterduolog/SKILL.md:18High confidence
Signal confidence: 7 facts
- Dangerous shell operation in code of the SKILL.mdduolog/SKILL.md:19High confidence
- Network access in code of the SKILL.mdduolog/SKILL.md:19High confidence
- Network access in code of the SKILL.mdduolog/SKILL.md:25High confidence
- Dangerous shell operation in code of the SKILL.mdduolog/SKILL.md:18High confidence
- Network access in code of the SKILL.mdduolog/SKILL.md:18High confidence
- Network access in code of the SKILL.mdduolog/SKILL.md:24High confidence
- Access to secrets in prose of the SKILL.mdduolog/SKILL.md:46Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md plugin/claude/skills/duolog/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugin/claude/skills/duolog/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugin/claude/skills/duolog/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugin/claude/skills/duolog/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugin/claude/skills/duolog/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.