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/foresightgit 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 | $0.00039 | $0.01066 |
| Opus 5 | $0.00019 | $0.00533 |
| Sonnet 5 | $0.00008 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
foresight 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cog Foresight
Strategic foresight — connecting dots across domains. Future-facing.
This is NOT reflect (past-facing) or evolve (system architecture). Foresight scans broadly and projects trajectories.
Memory Path
All files under the resolved memory path: $COG_HOME/memory/ if COG_HOME is set, otherwise ~/cog/memory/.
Minimum Data Check
Before scanning, verify there's enough material for meaningful foresight:
- If total observations across all domains < 10: stop. Say "Not enough history for strategic foresight. Keep capturing for a few more weeks."
- If only 1 domain has data: say "Foresight works best with 2+ active domains (it connects dots between them). Consider adding more domains or building out existing ones."
- If no action items exist: say "No active items to assess velocity on. Capture some tasks first."
Don't force a nudge from thin data. One honest "not yet" is better than a weak insight.
Files to Read
Read broadly — this is a scan:
- Read
memory/domains.ymlto discover all active domains - For each domain:
hot-memory.md+action-items.md - Also read:
memory/hot-memory.md(cross-domain context)memory/personal/entities.md(birthdays, relationships)memory/personal/calendar.md(upcoming events)memory/personal/health.md(health trajectory)- Recent observations across all domains (last 7 days)
- Thread current-state sections
Process
1. Cross-Domain Convergence
Look for topics, people, or themes appearing in 2+ domains simultaneously. These are convergence points — where effort in one area compounds into another.
2. Velocity & Stall Detection
Classify active items:
- Accelerating — multiple updates last week. Signal: ride the wave.
- Cruising — steady progress. Signal: nothing to flag.
- Stalling — no movement 2+ weeks. Signal: blocked or lost priority?
- Dormant — domain silence 4+ weeks. Signal: conscious or drift?
3. Timing Awareness
Read calendar and entities for events in next 2-4 weeks. Things that should start NOW to be ready later.
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 · 120 lines · 39 tokens per session scan A 8252cc63d3d8
foresight is a command published in the GitHub repository marciopuga/cog (376 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,066 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
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.