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.
git clone --depth 1 https://github.com/jonase47/ccprWrote 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/jonase47/ccpr/instinct)<a href="https://agentmods.dev/commands/jonase47/ccpr/instinct"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/instinct/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/jonase47/ccpr/instinct"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/instinct.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 | $0.01180 |
| Opus 5.5 | $0.00000 | $0.00472 |
| Sonnet 5.5 | $0.00000 | $0.00236 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
instinct 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instinct Management
Manage instincts (confidence-based rules from session experience).
Actions
Determine the desired action from $ARGUMENTS:
list – Show all instincts
- Read
~/.claude/instincts.md(slim global Tier-1 index) — one-liner per entry already gives ID + confidence + theme - Optional: load any of the topic files
~/.claude/instincts/{agents,files,workflow,shell-git,external}.mdfor full Rule/Why/How when the user wants details - Search all
docs/memory/*/instincts.md(agent instincts) - Check whether
docs/instincts.mdexists (project instincts) - Check whether
docs/memory/MEMORY.mdexists (project memory as cross-reference) - Show all instincts grouped by scope (Global / Agent / Project) with ID and confidence
- If project memory exists: show number of memory entries as info
add [rule] – Create a new instinct
- Ask the user for the scope:
- Global (
G-NNN): Applies to all agents → add the H3 Rule block to the matching topic file under~/.claude/instincts/{theme}.md, then add a one-liner bullet to~/.claude/instincts.md(slim index). Pick the topic file by domain (agents / files / workflow / shell-git / external). - Agent (
XX-NNN): Applies to one agent →docs/memory/{agent}/instincts.md - Project (
P-NNN): Applies only in the current project →docs/instincts.md
- Global (
- Generate the next available ID for the chosen scope
- Create the instinct with confidence 0.4:
### [ID] Short title
- **Confidence**: 0.4
- **Source**: User feedback from DD.MM.YYYY
- **Last confirmed**: DD.MM.YYYY
- **Rule**: [Rule from $ARGUMENTS]
- **Context**: [Ask the user for the context]
- Add it to the chosen file (global → topic file + index bullet; agent → that agent's instincts.md; project → docs/instincts.md)
- Update "Last updated"
confirm [ID] – Confirm an instinct
- Find the instinct with the given ID (global, agent, or project)
- Increase confidence by 0.1 (max 0.9)
- Update "Last confirmed" to today
- Show the updated instinct
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.
- 1mo ago Changed 6077b6857d73
- 1mo ago Changed · +3 lines 322b73352069
- 1mo ago First seen · 89 lines · 0 tokens per session scan A ea0182ddac04
instinct is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,180 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
context-prime
Generate a highly structured, copy-paste-ready context block from the current conversation for cold-starting a new session. Produces a YAML-fronted Markdown block optimized for an LLM/AI to quickly gain situational awareness, including skills/agents used and a resume hint for checkpoint continuation. Optionally focus…
diary
Create a session diary entry to document development progress, decisions, and handoff context.
forge-compact-task
Compact context with dotforge-standardized hint that preserves decisions, files modified, pending TODOs, behaviors disabled, and last commit. Use at 80% context window instead of waiting for auto-compact.
pack
Pack target repo with repomix. Snapshot for AI context. Cached per featureid.
cap
Shorthand for /forge capture — register a practice or insight in practices/inbox/.
setup
Interview me and scaffold my personal chief-of-staff system (context file, memory, task list, daily brief).