What is aget-enhance-health?

A health-remediation process that uses the findings from a health check, sorts them into severity levels, and verifies the result afterward.

Use it to run or consume an agent health check, apply Tier-A fixes, classify Tier-B and Tier-C findings, perform dry runs, and re-check health.

It turns detected problems into a defined response, while separating fixes that can be made now from issues that need backlog work or escalation.

How aget-framework/aget configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to aget-framework/aget. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/aget-framework/aget/main/.claude/skills/aget-enhance-health/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/aget-framework/aget

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aget-framework/aget/aget-enhance-health/github.svg)](https://agentmods.dev/skills/aget-framework/aget/aget-enhance-health)

Your own site

<a href="https://agentmods.dev/skills/aget-framework/aget/aget-enhance-health"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-enhance-health/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aget-framework/aget/aget-enhance-health"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-enhance-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,188 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00053	$0.03188
Opus 5	$0.00026	$0.01594
Sonnet 5	$0.00011	$0.00638
Haiku 4.5	$0.00005	$0.00319

Measured 11d ago against content hash 104f2360dabd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aget-enhance-health 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 11d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

aget-enhance-health — 100% identical, 6 lines differ

.claude/skills/aget-enhance-health/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aget-enhance-health

Remediate agent health drift. Consumes /aget-check-health output, classifies findings by severity Tier (A/B/C), applies Tier-A in-skill, routes Tier-B to backlog, escalates Tier-C via /aget-file-issue, and re-verifies. Instantiates the canonical check → enhance pipeline (DESIGN_DIRECTION §Principle 9) for the health domain.

This is the Generator layer (ADR-008 step 3), built on /aget-check-health (Advisory/detect) and scripts/health_check.py (implementation substrate). Governing spec: AGET_SESSION_SPEC CAP-SESSION-014.

Input

$ARGUMENTS - Optional check-health output path or invocation flag.

Format:

/aget-enhance-health — run /aget-check-health inline, then enhance
/aget-enhance-health <path-to-json> — consume pre-existing check output
/aget-enhance-health --tier A — apply only Tier-A remediations (skip B/C)
/aget-enhance-health --dry-run — classify findings but do not remediate

Execution

Phase 0: Diagnose

Objective: Obtain current check-health state. Either consume existing output or run inline.

Execute:

Check for input JSON path in arguments

If no input, invoke /aget-check-health --json and capture output:

python3 scripts/health_check.py --json > /tmp/aeh_check_$$.json

Parse findings — enumerate each WARN and ERROR
If no findings (status = HEALTHY): report "No remediation needed" and exit with Skill Completion Signal

User Checkpoint: Present findings summary:

Health Check Findings:
  Status: [HEALTHY/WARNINGS/ERRORS]
  WARN count: <n>
  ERROR count: <n>

Proceed to classification? (yes/adjust/abort)

Exit Criteria: Findings captured. User approved progression or skill exited clean.

Phase 1: Classify (Tier A/B/C)

Objective: Assign severity Tier to each finding per DESIGN_DIRECTION §enhance verb model.

Execute:

For each finding, evaluate:
- Tier-A (trivially fixable, applied in-skill): ALL of (a) reversible via git revert, (b) bounded to invoking agent's tree, (c) idempotent
- Tier-B (structural-bounded, routed to backlog): affects single artifact but needs broader review or cross-agent input
- Tier-C (scope-affecting, escalated via issue): multi-agent, multi-repo, or policy-level implications
If a finding is ambiguous between Tiers, default to the higher Tier (more cautious) and document ambiguity

Produce classification table:

| # | Finding | Tier | Rationale | Proposed Action |
|---|---------|:-:|-----------|-----------------|

Read the full file on GitHub · 273 lines

Changes

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.

11d ago First seen · 273 lines · 53 tokens per session scan A 104f2360dabd

Subscribe to this mod's changes

aget-enhance-health is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,188 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 2026-08-30.

Debugging agent-governance aget-framework ai-agents cli fleet-management human-ai-collaboration

aget-check-health

Run AGET health inspection and housekeeping checks. Detect-only — pair with /aget-enhance-health for remediation.

aget-framework/template-advisor-aget · 26 tokens

aget-close-project

Close a PROJECTPLAN with verifiable-assertion gate (V-tests + commits + retrospective), deferred-surface scan for next-plan handoff, and status transition (ACTIVE → COMPLETE / CLOSED / ABANDONED / SUPERSEDED). Strict counterpart to /aget-create-project (D71 Layer 2). Closes asymmetric verb-pair gap at PROJECTPLAN…

aget-framework/template-advisor-aget · 78 tokens

aget: Skill for Claude Code