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/bayramannakov/claude-reflect/view-queuegit clone --depth 1 https://github.com/BayramAnnakov/claude-reflectWhat 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 | $0.00007 | $0.00908 |
| Opus 5 | $0.00003 | $0.00454 |
| Sonnet 5 | $0.00001 | $0.00182 |
| Haiku 4.5 | $0.00001 | $0.00091 |
Grade A, and why
view-queue 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Queue file: per-project at
~/.claude/projects/<encoded-cwd>/learnings-queue.json - Legacy global queue (
~/.claude/learnings-queue.json) is auto-migrated on first access
Your Task
Display the current learnings queue in a readable format with confidence scores, patterns, and relative timestamps.
Output format:
════════════════════════════════════════════════════════════
LEARNINGS QUEUE: [N] items
════════════════════════════════════════════════════════════
[0.85] "use gpt-5.1 not gpt-5" (use-X-not-Y) - 2 days ago
[0.70] "perfect, that's exactly right" (positive) - 5 days ago
[0.90] "remember: always run tests" (explicit) - just now
════════════════════════════════════════════════════════════
Commands:
/reflect - Process and save learnings
/skip-reflect - Discard all learnings
════════════════════════════════════════════════════════════
If queue is empty:
════════════════════════════════════════════════════════════
LEARNINGS QUEUE: Empty
════════════════════════════════════════════════════════════
No learnings queued. Use "remember: <learning>" to add items,
or corrections will be auto-detected. Run /reflect to process.
════════════════════════════════════════════════════════════
Implementation
Step 1: Read the project-scoped queue file:
python3 scripts/read_queue.py 2>/dev/null || echo "[]"
Step 2: Parse and format each item with:
- Confidence score:
[0.XX]format, fromitem.confidence(default 0.60 if missing) - Message preview: First 50 chars with "..." if longer, from
item.message - Pattern name: In parentheses, from
item.patterns(show first pattern if multiple) - Relative timestamp: Human-readable time difference from
item.timestamp
Relative time calculation:
Calculate the difference between now and item.timestamp (ISO 8601 format):
- Less than 1 minute → "just now"
- Less than 1 hour → "X minutes ago"
- Less than 24 hours → "X hours ago"
- Less than 7 days → "X days ago"
- Otherwise → "X weeks ago" or show date
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 · 104 lines · 7 tokens per session scan A d953e3bfe6bf
view-queue is a command published in the GitHub repository BayramAnnakov/claude-reflect (1,425 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 908 once invoked, about $0.0000 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.