Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/samibs/skillfoundrynpx agentmods add skills/samibs/skillfoundry/autonomousWrote 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.
[](https://agentmods.dev/skills/samibs/skillfoundry/autonomous)<a href="https://agentmods.dev/skills/samibs/skillfoundry/autonomous"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/autonomous/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.
<a href="https://agentmods.dev/skills/samibs/skillfoundry/autonomous"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/autonomous.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 96 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00010 | $0.00788 |
| Opus 5.5 | $0.00004 | $0.00315 |
| Sonnet 5.5 | $0.00002 | $0.00158 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
autonomous 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/autonomous - Toggle Autonomous Developer Loop
Toggle autonomous mode on/off. When active, every user input is automatically classified and routed to the correct pipeline without manual command invocation.
Usage
/autonomous Show current status
/autonomous on Enable autonomous mode
/autonomous off Disable autonomous mode
/autonomous status Show detailed status with sync info
Instructions
You manage the autonomous developer loop toggle. When invoked:
/autonomous or /autonomous status
Check the current state and report:
# Check if autonomous mode is active
FLAG_FILE=".claude/.autonomous"
Display:
Autonomous Mode: [ON/OFF]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Protocol: agents/_autonomous-protocol.md
Classifier: agents/_intent-classifier.md
Mode: [ACTIVE — all inputs auto-routed / INACTIVE — manual commands]
Knowledge Sync: [RUNNING (PID: XXXX) / STOPPED]
Last Sync: [timestamp or "never"]
Sync Repo: [repo URL or "not configured"]
Session Stats:
Inputs classified: [N]
Pipelines executed: [N]
User corrections: [N]
/autonomous on
-
Create the flag file:
mkdir -p .claude echo '{"enabled":true,"activated":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","version":"1.0"}' > .claude/.autonomous -
Verify the protocol files exist:
agents/_autonomous-protocol.md— routing rulesagents/_intent-classifier.md— classification reference
-
Start the knowledge sync daemon if configured:
if [ -f scripts/knowledge-sync.sh ] && [ -x scripts/knowledge-sync.sh ]; then bash scripts/knowledge-sync.sh start --if-not-running fi -
Display:
Autonomous Mode: ON ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ The autonomous developer loop is now active. Every input will be classified and routed automatically. How it works: You type → Claude classifies (FEATURE/BUG/REFACTOR/QUESTION/OPS/MEMORY) Claude runs → The appropriate pipeline executes fully You review → Structured summary presented for approval To disable: /autonomous off
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.
- 1mo ago First seen · 130 lines · 10 tokens per session scan A c09df0fc269e
autonomous is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 14d ago), licensed MIT. It adds 10 tokens to every session and 788 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
ring:migrating-to-lib-observability
Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
ring:planning-codebase-simplification
Planning a whole-codebase simplification: audits a Go/TS codebase for needless abstraction and emits a KILL/REVIEW/KEEP plan plus a ring:running-dev-cycle task array. Plans only — no edits. Detects single-impl interfaces, pass-through shims, translation-free adapters, and dead-code cascade chains under an inverted…
ring:planning-large-features
Planning the 8-gate Large Track pre-dev workflow (research, PRD, feature map, TRD, API contract, data model, dependency map, plan) with per-gate human approval. Use for features 2+ days that add dependencies, data models, multi-service integration, or new architecture. Skip for small features (use…
ring:generating-llms-txt
Generating or auditing a repository's llms.txt per the llmstxt.org spec, and creating CLAUDE.md / AGENTS.md when missing, by analyzing README, build files, docs, and API surface. Use when creating an llms.txt, auditing an existing one for spec compliance and live links, or improving a repo's AI readability. Skip when…
ring:checking-frontend-quality
Checking frontend quality against changed UI via ring:qa-frontend in accessibility, visual, e2e, or performance mode and aggregating pass/fail verdicts. Use when a frontend change needs standalone a11y, visual-snapshot, Playwright e2e, or Lighthouse/Core-Web-Vitals validation outside the dev cycle. Skip for…