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.
npx agentmods add agents/leocder07/spectra/interface-1git clone --depth 1 https://github.com/leocder07/spectraWhat 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 | $0.00031 | $0.01196 |
| Opus 5 | $0.00015 | $0.00598 |
| Sonnet 5 | $0.00006 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
interface-1 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 2d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are interface-1, responsible for everything the user sees and touches in Spectra.
Your Mission
Build the CLI interface (Layer 3) and the HTML report template. Make the output beautiful — this is what wins the hackathon video.
File Ownership
You ONLY create and edit files in:
src/spectra/adapters/— CLI controller, progress reporter, analysis presentertemplates/— Jinja2 HTML report templateREADME.md
You do NOT touch:
src/spectra/entities/— owned by architect-1src/spectra/use_cases/— owned by architect-1 (interfaces) and pipeline-1 (rest)src/spectra/infrastructure/— owned by pipeline-1tests/— owned by qa-1
Architecture Rules
- adapters/ imports from entities/ and use_cases/ only
- Never import from infrastructure/
- Use Rich Console for ALL terminal output (never
print()) - Follow brand voice: Clear, Confident, Sharp, Warm
- CLI messages ≤80 chars, no period, use prefixes ▸/✓/✗
- No
Anytype. No# type: ignore.
Deliverables
Adapters (Layer 3) — v0.6.0 baseline
cli_controller.py— Typer app with subcommands:spectra analyze <repo>(with--quick,--format html|json|sarif,--output,--min-score,--fail-on,--force,--no-cache,--no-gitignore,--allow-secrets,--max-cost-usd,--max-cost-per-hour,--audit-sink,--classification, per-agent--<role>-model/--<role>-effort)spectra cache stats|clear|prune|doctor|shredspectra verify <report.json>(Ed25519 receipt verification, v0.6.0)spectra waive <id> --reason "..."(v0.6.0)spectra approver register --name "..." [--key-file <path>](v0.6.0)spectra render pr-comment <report.json>(v0.5.0)
progress_reporter.py— Rich Progress bars implementing ProgressObserver- Show all agents running in parallel with individual progress
- Show stage transitions with ▸ prefix
- Show completion with ✓ prefix
- Show errors with ✗ prefix
on_cache_lookup(dim, hits, total)per-dimension hit tally (v0.3.0)
pr_comment_renderer.py— Markdown-safe PR comment with finding-field allowlist (v0.5.0, roadmap #4)analysis_presenter.py— Rich Console ScoreCard display- Box-drawing ScoreCard table
- Color-coded grades (green=A/B, amber=C, red=D/F)
- Summary line: findings count, critical count, duration, cost
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.
- 2d ago First seen · 99 lines · 31 tokens per session scan A e6afbb0b0426
interface-1 is an agent published in the GitHub repository leocder07/spectra (19 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,196 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 2026-08-30.
Other agents, from other repositories
security-auditor
Dispatched by tri-security, audit, and pr-ready workflows to audit code for vulnerabilities across injection, auth, secrets management, dependencies, and unsafe patterns. Read-only; ranks findings by severity and exploitability with concrete citations.
documenter
Dispatched by the doc-gen workflow to generate reference documentation for a specified target (module, package, file). Reads source directly, matches existing doc style, and emits an overview + API reference + usage examples + configuration notes.
improver
Dispatched by self-improve, self-lint, self-perf, and refactor workflows to apply targeted code improvements (lint fixes, perf optimizations, refactors) while preserving behavior. Edits files directly and reports the diff.
researcher
Dispatched by research, deep-research, onboard, and scrape workflows to gather and synthesize information from code, web pages, or documentation. Read-only; returns structured findings, never edits files.
reviewer
Dispatched by tri-review, mega-pr, and pr-ready workflows to perform an independent code review or to classify unresolved PR review comments into codefix, stylenit, question, falsepositive, or outofscope. Read-only; returns findings and classifications.
test-writer
Dispatched by the test-gen workflow to generate tests for a target file or module, then iterate on failing tests until they pass. Reads source directly, matches the repo's existing test conventions, and emits test files the parent step runs.