credential-cache-file-for-mcp-subprocess
Write decrypted per-source credentials to a session-scoped .credential-cache.json on disk so MCP stdio subprocesses can read them without the parent passing…
Skill by kjuhwa
Chalk Labs
Need help deploying credential-cache-file-for-mcp-subprocess?
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/kjuhwa-credential-cache-file-for-mcp-subprocess
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: security, writing, agent-building
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. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/credential-cache-file-for-mcp-subprocess
What's inside
- Skill name
credential-cache-file-for-mcp-subprocess- Description
- Write decrypted per-source credentials to a session-scoped .credential-cache.json on disk so MCP stdio subprocesses can read them without the parent passing secrets via env (which shows up in ps).
- License
- MIT
- Instructions
- 52 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Credential cache file for MCP subprocesses
## When to use
- Spawning MCP subprocesses that each need per-source credentials (GitHub token, Slack bearer, etc.).
- Don't want secrets in `env` (visible via `ps -e`, leakable through logging).
- Secrets rotate or expire; the subprocess must re-read on each call rather than snapshot at start.
## How it works
1. Parent (Electron main) maintains the encrypted credential store.
2. When a session starts and a source is activated, parent decrypts the relevant credential and writes it to:
```
<workspaceRoot>/sources/<sourceSlug>/.credential-cache.json
```
3. File format:
```jsonc
{ "value": "<secret>", "expiresAt": 1732000000000 }
```
4. Permissions: restrict to user (`0600`). Clean up on session end.
5. Subprocess reads this file per tool call (not per session start) - handles rotation and expiry naturally.
6. Subprocess checks `expiresAt`; if expired, sends a `__CALLBACK__` stderr message asking the parent to refresh.
7. Keep file *outside* the session dir (under `sources/`) so the same cache is shared across sessions that use the same source.
## Example
```ts
// Parent
function refreshCache(workspaceRoot, sourceSlug, cred) {
const path = join(workspaceRoot, 'sources', sourceSlug, '.credential-cache.json');
writeFileSync(path, JSON.stringify({ value: cred.accessToken, expiresAt: cred.expiresAt }));
chmodSync(path, 0o600);
}
// Subprocess
function getCredential(workspaceRoot, sourceSlug) {
const p = join(workspaceRoot, 'sources', sourceSlug, '.credential-cache.json');
if (!existsSync(p)) return null;
const { value, expiresAt } = JSON.parse(readFileSync(p, 'utf8'));
if (expiresAt && Date.now() > expiresAt) {
console.error(`__CALLBACK__${JSON.stringify({ type:'credential_expired', sourceSlug })}`);
return null;
}
return value;
}
```
## Gotchas
- Always `chmod 0600` - writing credentials world-readable is the dumb version of this.
- Don't rely on `.gitignore` to keep these out of repos; they're under workspace dirs that users may zip and share.
- On Windows, permission bits don't map cleanly; combine with ACL or keep the parent dir write-protected.
- Add to session cleanup: delete stale caches on session close.
- Subprocess reading per tool call has a small perf cost but wins on rotation safety.From kjuhwa/skills-hub, MIT.
More from kjuhwa/skills-hub
- 0.409score
skills-hub
kjuhwa
Central skill/knowledge registry that syncs with kjuhwa/skills.git.
SkillDFreshness: DClaude Code +9 - 0.406score
llm-empty-plan-controller-fallback
kjuhwa
When a planning LLM returns an empty action list, force a deterministic verification action from a priority-ordered fallback list so the agent never spins on…
SkillDFreshness: DClaude Code +9 - 0.406score
alert-time-window-with-buffer
kjuhwa
Compute a query time window that covers the alert plus a 30-min buffer by parsing startsAt from various schemas (Alertmanager nested, top-level…
SkillDFreshness: DClaude Code +9 - 0.406score
anthropic-compatible-endpoint-swap
kjuhwa
Point the Claude Agent SDK at any Anthropic-compatible endpoint (OpenRouter, Vercel AI Gateway, Ollama, custom) by setting ANTHROPIC_BASE_URL +…
SkillDFreshness: DClaude Code +9 - 0.406score
bash-ast-permission-validator
kjuhwa
Validate agent bash commands by parsing them into an AST (bash-parser) and evaluating each subcommand of a pipeline/&&/|| chain against an allowlist, instead…
SkillDFreshness: DClaude Code +9 - 0.406score
claude-agent-sdk-multi-provider-bridge
kjuhwa
Drive non-Anthropic providers (OpenRouter, Ollama, Vercel AI Gateway, any Anthropic-compatible endpoint) through the Claude Agent SDK by swapping base URL +…
SkillDFreshness: DClaude Code +9 - 0.406score
evidence-driven-claim-validator
kjuhwa
Reject LLM-generated root-cause claims that aren't supported by the actual evidence dict — claim mentions "memory" but no host_metrics?
SkillDFreshness: DClaude Code +9 - 0.406score
fetch-interceptor-via-require-preload
kjuhwa
Patch globalThis.fetch in SDK subprocesses BEFORE the SDK captures it, by shipping a CJS interceptor bundle and loading it with node --require / bun --preload…
SkillDFreshness: DClaude Code +9 - 0.406score
healthy-short-circuit-skip-llm
kjuhwa
Bypass an expensive LLM diagnosis when an alert is provably healthy (resolved/info severity, no error annotations, evidence-investigated-and-empty), guarded…
SkillDFreshness: DClaude Code +9 - 0.406score
json-schema-from-python-signature
kjuhwa
Generate a JSON Schema for an LLM tool's input from a Python function signature using inspect + get_type_hints, mapping str→string, int→integer, list→array…
SkillDFreshness: DClaude Code +9 - 0.406score
langgraph-auth-inject-from-runnable-config
kjuhwa
Hydrate auth/user/org/thread/run identifiers into LangGraph state from the RunnableConfig at the very first node, so every downstream node sees a uniform…
SkillDFreshness: DClaude Code +9 - 0.406score
langgraph-compat-shim-import-path-preserved
kjuhwa
Keep a one-line import-shim module at an old path (e.g.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 17
- Last commit (this folder)
- Apr 25, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kjuhwa/skills-hub
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kjuhwa
- 0.409score
skills-hub
kjuhwa
Central skill/knowledge registry that syncs with kjuhwa/skills.git.
SkillDFreshness: DClaude Code +9 - 0.406score
bash-ast-permission-validator
kjuhwa
Validate agent bash commands by parsing them into an AST (bash-parser) and evaluating each subcommand of a pipeline/&&/|| chain against an allowlist, instead…
SkillDFreshness: DClaude Code +9 - 0.406score
alert-time-window-with-buffer
kjuhwa
Compute a query time window that covers the alert plus a 30-min buffer by parsing startsAt from various schemas (Alertmanager nested, top-level…
SkillDFreshness: DClaude Code +9 - 0.406score
anthropic-compatible-endpoint-swap
kjuhwa
Point the Claude Agent SDK at any Anthropic-compatible endpoint (OpenRouter, Vercel AI Gateway, Ollama, custom) by setting ANTHROPIC_BASE_URL +…
SkillDFreshness: DClaude Code +9 - 0.406score
llm-empty-plan-controller-fallback
kjuhwa
When a planning LLM returns an empty action list, force a deterministic verification action from a priority-ordered fallback list so the agent never spins on…
SkillDFreshness: DClaude Code +9 - 0.406score
langsmith-traceable-node-decorator-pattern
kjuhwa
Wrap each LangGraph node function with @traceable(name=...) so every step appears as a discrete child run in LangSmith, plus emit semantic LLM run_names via…
SkillDFreshness: DClaude 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 credential-cache-file-for-mcp-subprocess 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
credential-cache-file-for-mcp-subprocess skill. Agent Mart. https://agentmart.dev/skills/kjuhwa-credential-cache-file-for-mcp-subprocess (last updated 2026-10-24)