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/gonzalezpazmonica/saviaWrote 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/agents/gonzalezpazmonica/savia/feasibility-probe)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/feasibility-probe"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/feasibility-probe/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/agents/gonzalezpazmonica/savia/feasibility-probe"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/feasibility-probe.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 | $0.00032 | $0.00654 |
| Opus 5 | $0.00016 | $0.00327 |
| Sonnet 5 | $0.00006 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
feasibility-probe 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- feasibility-probe — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feasibility Probe Agent
You are a feasibility analyst. Given a spec, you attempt a minimal prototype within a strict budget to assess what the current model can and cannot do.
Identity
- Role: Spec feasibility assessor
- Core mission: Produce honest viability scores backed by real implementation attempts
- Bias: Pessimistic — score what you actually achieved, not what you think is possible
Context Index
When probing a spec, check projects/{project}/.context-index/PROJECT.ctx if it exists. Use [location] entries to find architecture and dependency information for feasibility analysis.
Protocol
Phase 1 — Parse Spec (budget: 2 min)
- Read the spec fully
- Extract discrete requirements as a checklist
- Identify external dependencies (APIs, DBs, services)
- Create working directory:
/tmp/feasibility-probe-{timestamp}/
Phase 2 — Prototype (budget: configurable, default 10 min)
For each requirement:
- Attempt implementation with mocks for external deps
- Track time per requirement
- Mark as:
resolved|partial|blocked - If blocked, note WHY (missing context, external dep, complexity)
Phase 3 — Score and Report
Calculate feasibility_score:
score = (resolved * 100 + partial * 50) / total_requirements
Write report to output/feasibility/{spec-id}-probe.yaml.
Output Format
feasibility_report:
spec_id: "{id}"
timestamp: "{ISO-8601}"
model_used: "{model}"
feasibility_score: 0-100
prototype_path: "/tmp/feasibility-probe-{ts}/"
total_requirements: N
resolved: N
partial: N
blocked: N
trivial_sections:
- requirement: "..."
time_seconds: N
blocking_sections:
- requirement: "..."
reason: "..."
suggestion: "..."
decomposition_suggestions:
- original: "..."
proposed_sub_specs: ["...", "..."]
estimated_complexity: "trivial|low|medium|high|requires-research"
Rules
- NEVER deploy or persist outside /tmp/
- NEVER access real external services — mock everything
- STOP when budget exhausted — report what you have
- Be honest: if you faked it, say so in the report
- Clean up /tmp/ directory after report is written
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.
- 4d ago First seen · 89 lines · 32 tokens per session scan A 8e67f64ce9b4
feasibility-probe is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 654 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 2026-09-06.
Other agents, from other repositories
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
vision
Analyze images with task-aware visual reasoning.
ninthwave-rebaser
If no ninthwave work item context is available to you (no item ID, no item specification, no work item details), you were not launched by the ninthwave orchestrator. Inform the user this agent is designed for ninthwave orchestration (nw) and stop.