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 skills add winstonkoh87/Athena-Public --skill therapeutic-ifsgit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/skills/winstonkoh87/athena-public/therapeutic-ifs)<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/therapeutic-ifs"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/therapeutic-ifs/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/skills/winstonkoh87/athena-public/therapeutic-ifs"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/therapeutic-ifs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.02516 |
| Opus 5 | $0.00017 | $0.01258 |
| Sonnet 5 | $0.00007 | $0.00503 |
| Haiku 4.5 | $0.00003 | $0.00252 |
Grade A, and why
therapeutic-ifs 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 12d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inner Work Engine (Schema + IFS)
Absorbs:
schema-deconstruction
Unified psychological intervention skill. Diagnoses maladaptive schemas (the what), then resolves them using IFS therapy (the how).
Triggers
"why do I keep doing this", "repeating pattern", "self-sabotage", "unpack this", "I'm stuck", "therapy mode", "ifs session", "procrastinating"
Phase 1: Schema Deconstruction (Diagnosis)
Step 1: The Structured Schema Interview
Ask these 5 questions in sequence. Each narrows the diagnostic field.
Q1: "What is the repeating behavior or pattern you want to understand?"
└── Target: Surface-level presenting problem
Example: "I keep hooking up with strangers"
Example: "I can't stop working even when exhausted"
Example: "I sabotage every relationship that gets close"
Q2: "When did this pattern START? What was happening in your life then?"
└── Target: Temporal origin — usually maps to a developmental wound
KEY: If origin predates age 12 → likely attachment-based
If origin is adolescence → likely identity/peer-based
If origin is adult → likely trauma-response or coping mechanism
Q3: "What does the behavior GIVE you in the moment? (Not later. RIGHT NOW.)"
└── Target: The functional payoff — the need the behavior is serving
Common payoffs:
├── Validation ("someone wants me")
├── Control ("I chose this, it wasn't done TO me")
├── Numbness ("I don't have to feel the pain")
├── Connection ("it's the closest I get to being held")
└── Identity ("this is who I am now")
Q4: "What happens AFTER? How do you feel 24 hours later?"
└── Target: The cost loop — if payoff fades and shame/emptiness returns,
the behavior is a Firefighter (see Phase 2), not a genuine need-met.
Q5: "If you STOPPED this behavior completely, what feeling would
you have to sit with?"
└── Target: The Exile — the wounded part the behavior is protecting.
Common Exiles:
├── Worthlessness ("I am fundamentally unlovable")
├── Abandonment ("everyone leaves")
├── Defectiveness ("something is wrong with me")
├── Invisibility ("no one sees me")
└── Powerlessness ("I have no control over what happens to me")
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.
- 12d ago First seen · 244 lines · 34 tokens per session scan A 506e61c45e0a
therapeutic-ifs is a skill published in the GitHub repository winstonkoh87/Athena-Public (587 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 2,516 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 skills, from other repositories
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
python-memory-safe-scripts
Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU…
feedback-workflow
A command-line workflow for reading and responding to approved software feedback. It keeps track of the feedback version, approval, work claim, evidence, and result.