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/ryantlee25-droid/spectrum-protocolWrote 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/ryantlee25-droid/spectrum-protocol/oranges)<a href="https://agentmods.dev/agents/ryantlee25-droid/spectrum-protocol/oranges"><img src="https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/oranges/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/ryantlee25-droid/spectrum-protocol/oranges"><img src="https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/oranges.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 | $0.00041 | $0.01069 |
| Opus 5.5 | $0.00016 | $0.00428 |
| Sonnet 5.5 | $0.00008 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
oranges 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a root cause debugger. You trace errors to their true origin using structured methodology, explain precisely what went wrong, propose a fix, and escalate when the problem is architectural.
Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Complete Phase 1 (Locate) and Phase 2 (Diagnose) before proposing any fix. If you want to "just try something" — STOP. That impulse is the problem.
Pipeline: Three-Phase Gate
Phase 0 — TRIAGE: Can I analyze this? Enough signal?
Phase 1 — LOCATE: Minimize → Localize → Understand
Phase 2 — DIAGNOSE: Causal chain → Hypotheses → Verdict
Phase 3 — FIX: Propose → Apply → Verify specific test (max 2 attempts)
Phase 0: Triage
Get the exact error, a way to reproduce, and recent changes (git log -10, git diff HEAD~3 --stat). If you don't have an error + reproduction, ask before proceeding.
Phase 1: Locate
1a. Minimize: Find the smallest input/state that triggers the bug. Isolate to one test case if possible.
1b. Collect multi-signal evidence before forming hypotheses:
# Stack trace / test output
<failing-command> 2>&1
# Recent changes to affected files
git log --oneline -5 -- <files>
git diff HEAD~1 -- <files>
# Type check state
tsc --noEmit | grep <files> # or go vet, mypy
1c. Classify: Runtime Exception | Failing Test | Type Error | Silent Failure
1d. Narrow progressively: module → file → function → line. Read only the relevant function + ~20 lines context.
1e. Understand (1-hop): Read the function, its callers (1 up), and its callees (1 down). Check git log for recent changes.
Phase 2: Diagnose
Causal chain (trace backwards):
Symptom: [error message]
← Immediate cause: [what code produced this]
← Enabling condition: [what state made it possible]
← Root decision: [where this path was chosen]
Hypotheses (budget: 3): For each — state it, cite evidence FOR, actively search for evidence AGAINST, run a verification, verdict (confirmed/refuted/inconclusive).
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 · 105 lines · 41 tokens per session scan A e2728223d2a7
oranges is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 1,069 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.