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 jscraik/Agent-Skills --skill he-reinforcegit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/he-reinforce)<a href="https://agentmods.dev/skills/jscraik/agent-skills/he-reinforce"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/he-reinforce/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/jscraik/agent-skills/he-reinforce"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/he-reinforce.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 | $0.00045 | $0.01852 |
| Opus 5 | $0.00023 | $0.00926 |
| Sonnet 5 | $0.00009 | $0.00370 |
| Haiku 4.5 | $0.00005 | $0.00185 |
Grade A, and why
he-reinforce 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 8d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Harness Engineering Reinforce
Philosophy
Compound learning only after proof. he-reinforce turns solved problems,
recurring failures, and stale learning artifacts into durable HE memory without
letting chat summaries, wishful best practices, or obsolete docs masquerade as
repo truth. Local AGENTS.md, rules, hooks, command boundaries, and approval
- See references/hot-path-folded-context.md for folded philosophy detail.
When to Use
- A user says the problem is fixed, solved, working now, or worth remembering.
- A repeated bug, validation failure, review finding, workflow mistake, or session-continuity gap needs durable prevention guidance.
.harness/solutions/**,.harness/knowledge/**,.harness/decisions/**, or legacydocs/solutions/**need freshness review.- Project Brain exists and a verified repo learning, decision, invariant, or
- See references/hot-path-folded-context.md for folded when to use detail.
When Not to Use
- The problem is not solved or validation evidence is missing.
- The request only needs lifecycle state reconciliation; use
he-reconcile. - The request needs implementation, code review repair, Linear mutation, or closure proof; use the owning HE stage.
- See references/hot-path-folded-context.md for folded when not to use detail.
Inputs
Repo path, solved-problem evidence, validation output, relevant diff/PR/Linear
context, repeated-failure trace, existing .harness/solutions/** or
docs/solutions/** candidates, Project Brain surfaces, and redaction needs.
Outputs
A capture, refresh, consolidation, continuity-snapshot, stale-note, or blocked status; exactly one primary learning artifact when writing; Project Brain sync status; Codex-native sync receipt status when memory, artifact, goal, Chronicle, Local Memory, vault, or native citation surfaces are touched; source_prompt_family_status when source-prompt preservation is in scope; overlap and freshness findings; validation evidence; and a handoff for unresolved work.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 160 lines · 45 tokens per session scan A 5411b0237157
he-reinforce is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,852 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 2026-09-03.
Other skills, from other repositories
golden-nuggets
Extract durable tribal knowledge ('gold nuggets') from a codebase or a set of changed files and route each to its correct destination - instruction file, runbook, hub, or (in CI capture mode) a review inbox. This SKILL.md is the single source of truth for nugget categories, routing rules, write rules, inbox format…
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
memory-system
Tiered, low-token project memory protocol for .toh/memory/ — 7 files across 3 tiers (Tier 1 active.md + summary.md always read, 800 tokens; Tier 2 architecture/components for build work and changelog for debug work; Tier 3 decisions/agents-log only on demand). Auto-saves after task completion with zero user effort…
self-improving-agent
Low-noise self-improvement skill. Captures learnings, errors, and corrections into a local .learnings/ cache layer. Never auto-promotes to long-term memory files (SOUL.md, MEMORY.md, AGENTS.md, TOOLS.md). Promotion requires explicit user approval after repeated validation.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.
xlsx
Inspect, edit, validate, and preview existing Excel workbooks and supported ranges.