Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Floka-as/floka-marketplaceWrote 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/commands/floka-as/floka-marketplace/auto)<a href="https://agentmods.dev/commands/floka-as/floka-marketplace/auto"><img src="https://agentmods.dev/badge/commands/floka-as/floka-marketplace/auto/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/commands/floka-as/floka-marketplace/auto"><img src="https://agentmods.dev/badge/commands/floka-as/floka-marketplace/auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.01287 |
| Opus 5 | $0.00017 | $0.00643 |
| Sonnet 5 | $0.00007 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
auto 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 12d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge: Auto
Autonomous execution loop. The user defines the work, then comes back to a finished product. You handle the build → evaluate → fix cycle without intervention.
Process
1. Ensure a Contract Exists
- If an argument matches an existing contract in
.forge/contracts/, use it. - If no contract exists, run the
/forge:contractflow first (discuss gray areas, write contract). This is the only interactive part — the discussion matters, don't skip it. - If
--skip-discussis passed AND a contract already exists, skip straight to building.
2. Build Loop
Execute this loop autonomously:
WHILE contract has unchecked criteria:
1. Implement the next logical chunk of work
2. Run automated gates (from contract's Gates section, scoped to what changed)
3. If gates FAIL → fix and re-run (max 3 attempts per gate, then flag to user)
4. Update contract checkboxes for completed criteria — WITH EVIDENCE
5. Commit progress with descriptive message
6. Summarize state in ≤5 bullets, keep response concise, continue
Commit after each chunk, not at the end. This gives rollback points and shows progress.
Context management: After each committed chunk, keep your working state lean. Don't carry full file contents or exploratory output across chunks. When you need to investigate something across many files, delegate to a Task agent and get back a focused answer.
3. Self-Evaluate (Quick Pass)
Before spawning the formal evaluator, do a quick self-check:
- Re-read the contract
- Verify each criterion yourself by reading the code / running commands
- For each criterion, record the evidence (command output, file:line, behavior)
- Fix any obvious gaps
This catches easy misses without the cost of a sub-agent.
4. Formal Evaluate
Spawn the skeptical evaluator (same as /forge:evaluate):
- Fresh context sub-agent
- Reads contract + code changes
- Runs all gates from the contract
- Uses Playwright MCP for UI criteria (mandatory if frontend files touched)
- Writes verdict to
.forge/evaluations/<name>.md
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.
- 12d ago First seen · 123 lines · 34 tokens per session scan A b852b64d659e
auto is a command published in the GitHub repository Floka-as/floka-marketplace (7 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,287 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.