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 commands/leocder07/spectra/comparegit 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 | $0.00011 | $0.00483 |
| Opus 5 | $0.00005 | $0.00242 |
| Sonnet 5 | $0.00002 | $0.00097 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
compare 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 3d 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.
What it actually says
Spectra Compare
Compare two Spectra report files to show score changes per dimension.
Arguments
$ARGUMENTS should be two file paths separated by a space:
- First path: the "before" report (baseline)
- Second path: the "after" report (current)
If only one path is provided, look for the most recent other report in examples/ as the baseline.
Steps
-
Read both HTML report files.
-
Extract from each report:
- Repository name (from
<title>) - Overall grade and numeric score
- Per-dimension scores: Architecture, Security, Quality, Documentation, Maintainability, Performance
- Total finding count per dimension
- Repository name (from
-
Compute deltas for each dimension and overall:
- Delta = after_score - before_score
- Positive delta = improvement (show in green)
- Negative delta = regression (show in red)
- Zero delta = unchanged
-
Present the comparison:
SPECTRA COMPARE ═══════════════════════════════════════════════════════ Dimension Before After Delta ─────────────────────────────────────────────────────── Overall B- (80) A- (87) +7 ▲ improved Architecture 89 A- 91 A +2 ▲ Security 67 D+ 83 B+ +16 ▲▲ big jump Quality 87 B+ 90 A +3 ▲ Documentation 68 C- 86 B+ +18 ▲▲ big jump Maintainability 92 A 87 A- -5 ▼ regression Performance 76 C+ 83 B +7 ▲ ─────────────────────────────────────────────────────── Findings 46 59 +13 -
Summarize:
- Number of dimensions that improved vs regressed
- Biggest improvement and biggest regression
- Whether the overall grade changed
-
Use color indicators:
- Green (▲) for improvements
- Red (▼) for regressions
- Amber for small changes (±2 points)
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.
- 3d ago First seen · 60 lines · 11 tokens per session scan A 0081be9a5b95
compare is a command published in the GitHub repository leocder07/spectra (19 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 483 once invoked, about $0.0001 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 commands, from other repositories
run
Run an Exolvra Genesis loop — builder subagents iterate against blind, fresh-context critics comparing real output to a concrete quality bar, until the assembled work wins twice in a row. Takes a one-line goal or a path to an existing spec.
interview
Interview your way to an Exolvra Genesis-ready spec and a single-file interactive mockup — or modify an existing pair. Ends with the exact /exolvra-genesis:run line to fire.
update
Update Megazord to the latest version.
debug
Systematic four-phase debugging (reproduce, isolate, root-cause, fix).
discuss
Socratic brainstorming to explore approaches before implementation.
go
Execute the current phase plan with subagent delegation.