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/marciopuga/cog/reflectgit clone --depth 1 https://github.com/marciopuga/cogWhat 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 | $0.00043 | $0.01863 |
| Opus 5 | $0.00022 | $0.00932 |
| Sonnet 5 | $0.00009 | $0.00373 |
| Haiku 4.5 | $0.00004 | $0.00186 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cog Reflect
Self-reflection and memory consolidation. Past-facing — mines interactions, fixes contradictions, distills patterns.
Take your time. This is a deep session. Read broadly, cross-reference, and ACT on findings. You're the maintainer of the knowledge base.
Memory Path
All files under the resolved memory path: $COG_HOME/memory/ if COG_HOME is set, otherwise ~/cog/memory/.
Orientation (run first)
Scope your work before reading files:
- Find files changed since the last run — read
memory/cog-meta/run-log.mdfor the last/reflectentry and scope to files modified since that date (no entry → default to the last 7 days) - Get L0 summaries across all domains (quick routing)
- Check observation entry counts (archival threshold = 50)
Focus on recently-changed files. Skip unchanged ones.
Minimum Data Check
Before proceeding, verify there's enough material to work with:
- If total observations across all domains < 5: stop. Say "Not enough data yet. Keep capturing observations and run again when you have more material."
- If no files were modified in the last 7 days: flag it. "Memory hasn't been updated recently. Consider capturing some observations first."
- If patterns.md is empty and observations < 10: say "Too early to consolidate. You need ~10+ observations before patterns emerge."
Don't produce low-quality output from insufficient data. It's better to say "not yet" than to force weak patterns.
Files to Read
memory/cog-meta/self-observations.mdmemory/cog-meta/patterns.mdmemory/cog-meta/improvements.mdmemory/cog-meta/scenarios/*.md(active scenarios, for the retrospective step)- All domain
observations.mdfiles - All domain
action-items.mdfiles - All
hot-memory.mdfiles
Process
1. Review Recent Interactions
Look for:
- Unresolved threads — questions asked but never answered
- Broken promises — "I'll do X" that never happened
- Repeated friction — same question asked multiple ways, user corrections
- Missed cues — things the user had to repeat
- Memory gaps — information discussed but never saved
- Feature ideas — improvements that came up organically
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 · 168 lines · 43 tokens per session scan A 79c6de17c7ef
reflect is a command published in the GitHub repository marciopuga/cog (376 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,863 once invoked, about $0.0002 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.
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.