Borrowing it
Nothing to install: this file belongs to yyordanov-tradu/stock-scanner-mcp. 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/yyordanov-tradu/stock-scanner-mcp/main/.claude/commands/learn-from-pr.mdgit clone --depth 1 https://github.com/yyordanov-tradu/stock-scanner-mcpWrote 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/commands/yyordanov-tradu/stock-scanner-mcp/learn-from-pr)<a href="https://agentmods.dev/commands/yyordanov-tradu/stock-scanner-mcp/learn-from-pr"><img src="https://agentmods.dev/badge/commands/yyordanov-tradu/stock-scanner-mcp/learn-from-pr/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/commands/yyordanov-tradu/stock-scanner-mcp/learn-from-pr"><img src="https://agentmods.dev/badge/commands/yyordanov-tradu/stock-scanner-mcp/learn-from-pr.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 | $0.00000 | $0.00855 |
| Opus 5 | $0.00000 | $0.00428 |
| Sonnet 5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
learn-from-pr 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 11d 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
Extract lessons from a PR review and improve project standards. Argument: $ARGUMENTS (PR number or URL, or "last" for most recent reviewed PR).
Steps
-
Gather PR review findings
- If a PR number/URL is provided, fetch the review comments:
gh pr view <number> --comments - If "last" or no argument, check the current conversation for review findings
- If no findings anywhere, ask the user to provide the PR or paste findings
- If a PR number/URL is provided, fetch the review comments:
-
Categorize each finding For every issue raised in the review, classify it:
- Pattern violation — existing standard was broken (→ strengthen the standard or add enforcement)
- Missing standard — no rule existed to prevent this (→ add a new rule)
- Missing checklist item — a pre-merge check would have caught it (→ add to checklist)
- Test gap — a category of test was missing (→ add to testing standards)
- Informational — good practice, no action needed
-
Read current standards files
- Read
docs/development-standards.md— architecture, patterns, naming, testing, error handling - Read
docs/pre-flight-checklist.md— pre-flight steps - Read
CLAUDE.md— project overview and key rules
- Read
-
Cross-reference with actual codebase Before drafting any rule change, verify it against the real code:
- Read representative module implementations (e.g.,
src/modules/finnhub/client.ts, newest module) to confirm patterns - Check that examples in standards (header names, type names, file names) match real code
- If a proposed rule would contradict existing merged code, adjust the rule — not the code
- Read representative module implementations (e.g.,
-
Draft proposed changes For each non-informational finding, propose a specific edit:
- Identify the exact section in the target file
- Write the new/updated text
- Explain why (link to the PR finding)
Before presenting changes, self-check for these common mistakes:
- Duplication — does the new rule repeat something already stated elsewhere in the same file? Search for keywords.
- Contradiction — does the new rule conflict with an existing rule? If so, update the existing rule rather than adding a contradictory one.
- Wrong specificity — does the rule use module-specific terms (e.g.,
ScanRow[],scanner.test.ts) where it should be generic? Use general terms unless the rule truly applies to only one module. - Stale references — does the rule reference file names, header names, or type names that don't exist in the codebase? Verify against actual code.
- CLAUDE.md consistency — if a rule is added/changed in
development-standards.md, does the corresponding summary inCLAUDE.mdneed updating? Always check. Also check if module counts, version numbers, env vars, or project structure inCLAUDE.mdare affected. - Hard vs. soft rules — use MUST only for true invariants. If exceptions exist (even one merged module), use SHOULD with a documented deviation process.
Present ALL proposed changes to the user for approval before editing.
-
Apply approved changes
- Edit the target files with the approved changes
- Keep existing formatting and style consistent
- Do NOT remove or weaken existing rules — only add or strengthen
-
Verify consistency (post-edit)
- Re-read edited files and confirm no duplication or contradiction was introduced
- Check that CLAUDE.md summary rules still match the detailed standards
- Check that CLAUDE.md project metadata (version, module count, tool count, env vars, structure) is current
- If CLAUDE.md needs updating to reflect new rules or changed project state, update it
-
Report
- Summarize what was added/changed
- List any findings that were skipped and why
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.
- 11d ago First seen · 59 lines · 0 tokens per session scan A 03104fb69dc1
learn-from-pr is a command published in the GitHub repository yyordanov-tradu/stock-scanner-mcp (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 855 tokens. 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 commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.