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/not-diamond/self-care/contextgit clone --depth 1 https://github.com/Not-Diamond/self-careWhat 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 | $0.00010 | $0.00985 |
| Opus 5 | $0.00005 | $0.00492 |
| Sonnet 5 | $0.00002 | $0.00197 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
context 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Care Context
View or edit the agent context file that helps Self-Care understand your agent's expected behavior.
Context File Location
Agent context is stored in: .self-care/context.md
This free-form description is provided to all analysis skills to help them understand what's normal vs problematic for your specific agent.
Instructions
Parse Arguments
Extract the subcommand from $ARGUMENTS:
- If empty or whitespace-only: prompt for new context
- If
show: display current context - If
reset: reset to default template - Otherwise: show usage help
Prompt for New Context (no arguments)
-
Ensure the config directory exists:
mkdir -p .self-care/ -
Read current context at
.self-care/context.mdif it exists. -
Display current context (or note if empty/missing):
Current Agent Context ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ <current content, or "No context configured yet."> ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ -
Ask user for new context using AskUserQuestion:
- question: "Describe your agent's expected behavior. This helps Self-Care understand what's normal vs problematic. Include details like: what the agent does, expected tool usage patterns, intentional deviations from typical behavior."
- header: "Agent Context"
- options:
{ "label": "Keep current", "description": "Don't change the agent context" }{ "label": "Clear context", "description": "Remove the agent context file" }
-
Handle response:
- If user selects "Keep current": stop, no changes.
- If user selects "Clear context": delete the file and confirm:
Then display:rm -f .self-care/context.mdAgent context cleared. - If user provides free text (via "Other"): continue to step 6.
-
Write the new context using the Write tool:
# Agent Context <user's description>
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 · 165 lines · 10 tokens per session scan A 332fedb9bbb9
context is a command published in the GitHub repository Not-Diamond/self-care (28 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 985 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 2026-08-30.
Other commands, from other repositories
coder-eval-implement-plan
Implement an approved codereval plan phase by phase with risk-scaled per-phase review, then a final code review.
VibeGuard: Stats
View hooks trigger statistics - interception/warning/release times and reason analysis.
closeout
Close out a UNITARES workspace before final response.
checkin
Manual UNITARES governance check-in for the current turn.
re-review
Round 2+ review — confirm revisions landed, catch regressions, do not re-litigate.
project
Follow the project management workflow defined in .agents/skills/project/SKILL.md.