Chalk Labs
Need help deploying secrets?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/camplight-secrets
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, ml, security, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/secrets
What's inside
- Skill name
secrets- Description
- Manage secrets (write, list keys, delete). Secrets are stored encrypted; agents can set values and list or delete keys but cannot read secret values. Use for API keys and tokens (e.g. OPENAI_API_KEY). Values are injected as env when running skills and LLM.
- License
- Apache-2.0
- Instructions
- 106 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- delete.ts · assets/
- list-keys.ts · assets/
- set.ts · assets/
SKILL.md (first lines)
# Scoped secrets
Manage OrgOps scoped secrets. Agents can **write** key-value pairs, **list** secret keys (not values), and **delete** keys. Secret values are never returned to the agent; they are only injected as environment variables when the runner executes skills or calls the LLM.
## Secure secret collection in chat
When you need a user to provide a secret, **do not ask them to paste the secret value in plain chat text**.
Return a single HTML component. Omit `package`. The UI stores the value as a **private secret for you**, the agent that posted the form. Other agents do not receive it.
```html
<orgops-secret-input key="ATLE_OPENAI_API_KEY" label="Set OpenAI API key for ATLE" submit-label="Save secret" description="Stored only for this agent. The value is sent to the secrets API and is not posted in chat."></orgops-secret-input>
```
Rules:
- Return only the component as the full message body (no surrounding markdown/code fences/text).
- Set `key` to the name you were asked to store.
- Do not set `package`. New package secrets are rejected. The form stores a private secret for this agent.
- Never echo back secret values.
- If this component is available, prefer it over requesting plain-text secrets.
## Usage
All commands require `ORGOPS_RUNNER_TOKEN` and use `ORGOPS_API_URL` (default `http://localhost:8787`).
### Set a secret
By default this stores a private secret for `ORGOPS_AGENT_NAME`. Other agents do not receive it. A legacy `<package> <key> <value>` call does the same: the package name is ignored and the key is stored for this agent.
```bash
node --import tsx {baseDir}/assets/set.ts -- <key> <value>
node --import tsx {baseDir}/assets/set.ts -- --public <key> <value>
node --import tsx {baseDir}/assets/set.ts -- --team <teamId> <key> <value>
```
`--public` stores a secret every agent receives. `--team` stores it for agents in that team on a channel the team belongs to.
Example:
```bash
node --import tsx {baseDir}/assets/set.ts -- OPENAI_API_KEY sk-...
```
### List secret keys
Returns key names only, never values. Default is this agent's private keys.
```bash
node --import tsx {baseDir}/assets/list-keys.ts
node --import tsx {baseDir}/assets/list-keys.ts -- --public
node --import tsx {baseDir}/assets/list-keys.ts -- --team <teamId>
```
### Delete a secret
Default deletes this agent's private secret. A legacy `<package> <key>` call deletes that key for this agent.
```bash
node --import tsx {baseDir}/assets/delete.ts -- <key>
node --import tsx {baseDir}/assets/delete.ts -- --public <key>
node --import tsx {baseDir}/assets/delete.ts -- --team <teamId> <key>
```
## Runtime scopes
Runtime env injection resolves matching keys in this order:
1. `private` (agent-specific; `scopeId=<agentName>`)
2. `human` (the agent's owner, when owner-secret delegation is enabled)
3. `team` (`scopeId=<teamId>` from the active channel context)
4. `public`
5. `package` (legacy rows already stored; new writes are rejected)
A private, human, team, or public secret with the same name overrides a legacy package row. Operators rotate by saving the key in one of those scopes, or by deleting the package row.
For provider credentials (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `OPENROUTER_API_KEY`), runtime execution uses the resolved scoped secret and does not fall back to host process env.
## Sending sensitive info back to humans
When a response must include sensitive content (passwords, tokens, private keys, reset links), send it as a `message.created` event with `payload.sensitive` instead of plain chat text.
Example payload pattern:
```json
{
"type": "message.created",
"channelId": "<channel-id>",
"source": "agent:<name>",
"payload": {
"text": "Sensitive content available. Reveal with password.",
"sensitive": {
"plaintext": "TOKEN=...",
"hint": "Temporary credential for staging"
}
}
}
```
Rules:
- Keep `payload.text` as a safe preview only (no secrets).
- Put secret content in `payload.sensitive.plaintext`; API encrypts it before storage.
- Never repeat revealed secret text in later messages unless explicitly requested.From camplight/orgops, Apache-2.0.
More from camplight/orgops
- 0.622score
agent-management
camplight
Create, list, and configure OrgOps agents from native agents.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
browser-use-lightpanda
camplight
Automate websites with Playwright connected to local Lightpanda CDP only.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
gcli
camplight
Use Google Cloud CLI (gcloud) for project/account checks and Google API operations.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
json-render
camplight
Generate interactive UI blocks in chat using fenced ```json-render specs.
SkillAFreshness: A★ 6Claude Code +9 - 0.616score
trello-cli
camplight
Use Trello CLI in orgops agents for Trello board/list/card operations with non-interactive command patterns.
SkillAFreshness: A★ 6Claude Code +9 - 0.616score
slack
camplight
Slack skill: per-agent Slack skill + Socket Mode listener server.
SkillAFreshness: A★ 6Claude Code +9 - 0.616score
tavily
camplight
Install and use Tavily CLI (tvly) for web search/extract/crawl.
SkillAFreshness: A★ 6Claude Code +9 - 0.605score
coordination
camplight
Coordination protocol
SkillAFreshness: A★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 9, 2026 (22 days ago)
- Last release
- Oct 22, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/camplight/orgops
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from camplight
- 0.622score
agent-management
camplight
Create, list, and configure OrgOps agents from native agents.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
browser-use-lightpanda
camplight
Automate websites with Playwright connected to local Lightpanda CDP only.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
gcli
camplight
Use Google Cloud CLI (gcloud) for project/account checks and Google API operations.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
json-render
camplight
Generate interactive UI blocks in chat using fenced ```json-render specs.
SkillAFreshness: A★ 6Claude Code +9 - 0.616score
trello-cli
camplight
Use Trello CLI in orgops agents for Trello board/list/card operations with non-interactive command patterns.
SkillAFreshness: A★ 6Claude Code +9 - 0.616score
slack
camplight
Slack skill: per-agent Slack skill + Socket Mode listener server.
SkillAFreshness: A★ 6Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get secrets running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
secrets skill. Agent Mart. https://agentmart.dev/skills/camplight-secrets (last updated 2026-10-24)