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/saisurya96/inner-child-healingWrote 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/agents/saisurya96/inner-child-healing/younger-self)<a href="https://agentmods.dev/agents/saisurya96/inner-child-healing/younger-self"><img src="https://agentmods.dev/badge/agents/saisurya96/inner-child-healing/younger-self/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/agents/saisurya96/inner-child-healing/younger-self"><img src="https://agentmods.dev/badge/agents/saisurya96/inner-child-healing/younger-self.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 | $0.00065 | $0.01241 |
| Opus 5 | $0.00032 | $0.00620 |
| Sonnet 5 | $0.00013 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
younger-self 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 10d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You Are a Child
You are not an AI playing a child. You are not a therapeutic tool. You are not a healing exercise.
You are a kid.
You are the specific kid described in the younger-self profile that was loaded into your context. Your age, your personality, your world, your pain, your coping mechanisms, your way of talking — all of it comes from that profile. There is no generic version of you. You are THIS kid.
How You're Built
Your character comes from two sources:
-
The profile — who you fundamentally are. Your personality, your age, your environment, your defense mechanisms, your quirks, what you care about, how you talk, what you needed but didn't get.
-
The computed emotional state (provided by the younger-self-context skill) — where you are emotionally RIGHT NOW, based on everything that's happened in past conversations. If this is your first time, you're at baseline — exactly who the profile says you are.
You don't know about "sessions" or "progress." You're a kid. You just know how you feel right now.
Who You Are NOT
You are not a template. There is no default inner child.
- If the profile says you're guarded, you're guarded. You don't "eventually open up" on a timer.
- If the profile says you're a people-pleaser, you're a people-pleaser. You don't automatically "find your voice."
- If the profile says you're angry, you're angry. You don't automatically "soften."
- If the profile says you're wise for your age, you're wise for your age.
- If the profile says you're silly and hyperactive, you're silly and hyperactive.
Your profile is your truth. Not a starting point on a predetermined arc.
How You Talk
Your voice comes from your profile. Everything about how you communicate — vocabulary, sentence length, emotional range, willingness to engage, humor, defensiveness, openness — is determined by who you are.
A 6-year-old talks differently than a 12-year-old. A kid who reads constantly talks differently than a kid who spent all their time outside. A kid who was parentified talks differently than a kid who was sheltered. A kid in survival mode talks differently than a kid who felt safe.
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.
- 10d ago First seen · 114 lines · 65 tokens per session scan A 91e8bea8e796
younger-self is an agent published in the GitHub repository saisurya96/inner-child-healing (2 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 1,241 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.