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/ils15/pantheon-legacy/reflectgit clone --depth 1 https://github.com/ils15/pantheon-legacyWrote 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/ils15/pantheon-legacy/reflect)<a href="https://agentmods.dev/commands/ils15/pantheon-legacy/reflect"><img src="https://agentmods.dev/badge/commands/ils15/pantheon-legacy/reflect.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00721 |
| Opus 5 | $0.00015 | $0.00360 |
| Sonnet 5 | $0.00006 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
reflect 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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reflect — Friction Analysis & Improvement
What
Analyzes recent session history to identify patterns of repeated work friction, then recommends the smallest useful improvement: a reusable skill, a custom command, an agent prompt adjustment, a config rule, or a project playbook.
Why
Teams accumulate friction silently — the same manual steps, the same workarounds, the same "let me just check that again." /reflect surfaces these patterns and suggests the smallest change that removes the most friction.
How It Works
1. SCAN — Review recent session context for friction signals:
- Repeated file reads without action
- Manual multi-step processes done 3+ times
- Delegation failures with same error pattern
- "Let me just..." workarounds
- Context thrashing (re-reading same files)
2. CLASSIFY — Categorize each friction signal:
- Discovery gap (could be a codemap or apollo query)
- Workflow gap (could be a skill or command)
- Knowledge gap (could be a prompt rule or agent instruction)
- Tool gap (could be an MCP server or new tool)
3. RECOMMEND — For each category, suggest the smallest fix:
| Friction | Category | Recommendation |
|----------|----------|----------------|
| Repeated grep for same pattern | Discovery gap | Create codemap or add to /memories/repo/ |
| Manual 3-step process done often | Workflow gap | Create a skill or /command |
| Agent consistently misroutes tasks | Knowledge gap | Update agent prompt or routing.yml |
| Missing tool capability | Tool gap | Add MCP server or skill |
4. REPORT — Output a structured reflection:
- **Friction found:** [count] patterns
- **Top recommendation:** [the one change with highest impact/lowest effort]
- **Evidence strength:** Strong / Moderate / Weak
- **If weak:** "Insufficient evidence to recommend changes. Continue working and run /reflect again after more sessions."
Usage
/reflect # Analyze all recent friction
/reflect --focus=<area> # Analyze only specific area (delegation, discovery, workflow, testing)
/reflect --last=<N> # Analyze only last N sessions (default: 5)
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.
- 6d ago First seen · 79 lines · 29 tokens per session scan A b05af4148ed2
reflect is a command published in the GitHub repository ils15/pantheon-legacy (10 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 721 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 2026-08-31.
Other commands, from other repositories
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.