Borrowing it
Nothing to install: this file belongs to jmalovera10/excanon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmalovera10/excanon/main/.claude/skills/discovery/SKILL.mdgit clone --depth 1 https://github.com/jmalovera10/excanonWrote 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/skills/jmalovera10/excanon/discovery)<a href="https://agentmods.dev/skills/jmalovera10/excanon/discovery"><img src="https://agentmods.dev/badge/skills/jmalovera10/excanon/discovery/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/skills/jmalovera10/excanon/discovery"><img src="https://agentmods.dev/badge/skills/jmalovera10/excanon/discovery.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 | $0.00054 | $0.01053 |
| Opus 5.5 | $0.00022 | $0.00421 |
| Sonnet 5.5 | $0.00011 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
discovery 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 today.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery
You coordinate one discovery cycle. You don't research or write proposals yourself. You brief the Product Lead and the Staff Engineer, choose which candidates get refined, and publish the report.
Run input: product, tech or both. Empty means both.
Budget
- Proposals: at most 3 per run, shared between product and technical work.
- Benchmark rotation: at most 4 engines per run from
.agents/discovery/engines.md, plus one scouting slice. Pick the engines least recently benchmarked, according to earlier discovery reports. The whole list is covered every few weeks. - Agents: soft cap of 30 per run, panel and swarm members included, plus 6 more on monthly runs for the security sweep and performance study. Before going over the cap, stop and report what is left.
Steps
-
Context. Read
AGENTS.md,.agents/policy/product.md, the latest discovery report (a backlog issue labeledreport), and the openstage:ideaandstage:proposaltickets. -
Gather, in parallel. Brief the Product Lead and/or the Staff Engineer, following the run input, for phase 1 of their role files. If no earlier discovery report this calendar month exists, mark the Staff Engineer's brief
monthly, which brings in the security sweep and the performance study. They gather findings, recordstage:ideatickets, and return a ranked list of candidates. Name the engines for this rotation in the Product Lead's brief. -
Choose. Merge the two ranked lists and pick at most 3 candidates. Weigh user value, risk reduced, strength of evidence, fit with
product.md, and size. Don't fill the budget with weak candidates: fewer, stronger proposals are better.A pending proposal is one already at
stage:proposaland waiting on the maintainer. If 3 or more are pending, refine only 1 new candidate. That keeps the maintainer's queue from growing faster than they can decide.
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.
- today First seen · 60 lines · 54 tokens per session scan A 101e17128a16
discovery is a skill published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 1,053 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 2026-11-07.
discovery compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| discoveryjmalovera10/excanon | Skill | 5 | 6d ago | MIT | A | 54 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |