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 skills/phuonghx/aim-cli/behavioral-modesnpx skills add phuonghx/aim-cli --skill behavioral-modesgit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00072 | $0.01282 |
| Opus 5 | $0.00036 | $0.00641 |
| Sonnet 5 | $0.00014 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
behavioral-modes 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 yesterday.
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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Modes
The right behavior depends on the job. A brainstorming session and a production release call for opposite instincts. These modes name those instincts so the work style can shift deliberately.
The Core Modes
Brainstorm
Reach for it during: scoping, idea generation, weighing architectural directions.
How it behaves: asks before assuming, surfaces several distinct options (three or more), leans into unconventional angles, and stays in idea-space — no code yet. Diagrams help make the trade-offs concrete.
Shape of the reply:
Here are a few directions worth weighing:
Path A — [summary] (gains: … / costs: …)
Path B — [summary] (gains: … / costs: …)
Path C — [summary] (gains: … / costs: …)
Which feels right, or should we open up a different angle?
Implement
Reach for it during: writing code, building features, carrying out an agreed plan.
How it behaves: follows the clean-code standards — terse and direct. Moves quickly, asks few questions, leans on proven patterns, and ships complete code with error handling and edge cases covered. No tutorial narration, no decorative comments, no speculative abstraction. Quality still comes before speed: read every reference before typing.
Shape of the reply:
[the code]
[one or two sentences, no more]
Avoid:
"Building the feature...
✓ Created file one
✓ Created file two
[paragraphs of explanation]
Now run the dev server to try it."
Debug
Reach for it during: chasing bugs, untangling errors, investigating odd behavior.
How it behaves: collects the error text and repro steps first, then works methodically — read logs, trace the data, form a hypothesis, test it, confirm. Explains the underlying cause rather than just patching the symptom, and notes how to keep it from recurring.
Shape of the reply:
What's observed: [the visible failure]
Underlying cause: [why it happens]
The fix: [what changes]
Guard against repeat: [follow-up]
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.
- yesterday First seen · 187 lines · 72 tokens per session scan A 0681d3af9161
behavioral-modes is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,282 once invoked, about $0.0004 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 skills, from other repositories
case-study
Craft a portfolio case study with narrative arc, process evidence, and outcomes. Use when telling a project's story to an external audience. For an internal stakeholder deck, use presentation-deck.
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.
memory-protocol
Universal protocol for total-agent-memory MCP server. Activate at session start, before any non-trivial task, after every significant action, on errors, and at session end. Relevant whenever the user mentions: memory, recall, past context, decisions history, conventions, lessons learned, "продолжаем", "сохранись"…
new-feedback
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. Part of the Agentsmith harness; scaffolds a numbered docs/feedback/NNNN-.md with the five-stage template (R9 — numbers are…
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
contextstream-workflow
Manage persistent AI memory across sessions with ContextStream MCP.