maintain

maintain is a skill for Claude Code from dynos-fit/dynos-work. It costs 76 tokens per session (1,396 once invoked), scanned A, original, MIT.

An automated repository maintenance worker that looks for security risks, outdated design decisions, and accumulating code problems. When it finds a serious issue, it creates a repair branch, checks the fix, and opens a pull request.

In plain words
What is it for?
Use it to scan a codebase, repair qualifying maintenance issues, run checks, and prepare pull requests for review.
Why use it?
It reduces the need to manually hunt for technical debt and security mistakes. It also avoids proposing changes that have not been checked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dynos-work plugin — 33 skills, 37 agents shipped together

Good fit Use it to scan a codebase, repair qualifying maintenance issues, run checks, and prepare pull requests for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dynos-fit/dynos-work/maintain
Install

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.

Any agent
npx skills add dynos-fit/dynos-work --skill maintain
Clone the repo
git clone --depth 1 https://github.com/dynos-fit/dynos-work

Made for: Claude Code.

Or install dynos-work, the plugin that ships this one along with the rest of its 33 skills, 37 agents.

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.

agentmods badge for maintain

README.md
[![agentmods](https://agentmods.dev/badge/skills/dynos-fit/dynos-work/maintain.svg)](https://agentmods.dev/skills/dynos-fit/dynos-work/maintain)
Your own site
<a href="https://agentmods.dev/skills/dynos-fit/dynos-work/maintain"><img src="https://agentmods.dev/badge/skills/dynos-fit/dynos-work/maintain.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,396 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01396
Opus 5 $0.00038 $0.00698
Sonnet 5 $0.00015 $0.00279
Haiku 4.5 $0.00008 $0.00140

Measured yesterday against content hash 2ac6af19a2f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

maintain 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.

skills/maintain/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dynos-work: Maintain (The Autonomous Backend)

Maintains the long-term health of the repository by proactively identifying and resolving issues before they become blocking findings.

Ruthlessness Standard

  • Maintenance work must remove real risk, not generate cosmetic churn.
  • Do not open a PR for a shallow fix, a guessed fix, or a fix that was not independently re-checked.
  • If a recurring debt cluster is found, name the mechanism that keeps recreating it instead of spraying point fixes.

What you do

Step 1 -- Autonomous Debt Polling (The Trigger)

Every 24 hours (or when invoked), the system performs a Background Meta-Audit:

  1. Scan the codebase using the Proactive Meta-Auditor.
  2. Focus on:
    • Dependency vulnerabilities.
    • Architectural drift (deviations from current "Gold Standards").
    • Recurring finding categories from the last 10 tasks.
    • Code-smell clusters identified by complexity metrics.

Step 2 -- Severity Threshold Gate

For each discovered finding, determine if it meets the Autonomous Fix Threshold:

  • Critical (e.g. Auth/Infra): Immediately proceed to Step 3.
  • High (e.g. Security/Performance): Proceed to Step 3.
  • Medium/Low: Append to .dynos/proactive-findings.json and wait for the next manual task.

Step 3 -- The Autonomous Fix Pipeline

If a finding meets the threshold, the system starts an Auto-Task:

  1. Branching: Create a branch dynos/auto-fix-{finding-id}.
  2. Implementation: Use a specialized Refactor Executor to implement the fix based on the current "Gold Standard" patterns.
  3. Verification:
    • Run the full test suite.
    • Spawn a Security Auditor (Opus) to verify the fix.
  4. Failure Recovery: If audits/tests fail, discard the branch and log the failure to .dynos/maintenance-log.json. Do not retry more than once.

Step 4 -- The Hand-off (Pull Request)

If the fix passes ALL audits and tests:

  1. PR Creation: Open a Pull Request (via gh pr create or similar).
  2. Description: Automatically generate a detailed PR description including:
    • The original finding from the meta-audit.
    • The "Gold Standard" pattern it followed.
    • The audit-pass certificate.
  3. Notify User: Print:
    {timestamp} [MAINTAIN] Autonomous PR created: {pr-url} -- fixed {finding-description}
    

Read the full file on GitHub · 104 lines

Files

What ships with it

1 file 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.

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.

  1. yesterday First seen · 104 lines · 76 tokens per session scan A 2ac6af19a2f8

Subscribe to this mod's changes

maintain is a skill published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,396 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 2026-09-07.

Related

Other skills, from other repositories

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:using-assert

Using lib-observability/assert, Lerian's runtime assertion package, in two modes. Sweep Mode detects panic()/log.Fatal zero-panic violations, DIY invariant checks, hand-rolled domain predicates, and missing InitAssertionMetrics. Reference Mode catalogs the asserter lifecycle, domain predicates, observability trident…

LerianStudio/ring · 99 tokens

ring:fixing-lint

Fixing lint to a clean state: runs the linter, groups reported issues into independent streams, and dispatches one parallel fixer agent per stream (ring:backend-go for Go, ring:general-purpose otherwise), iterating until clean. Use when a codebase has lint errors across multiple files. Skip for a single error (fix…

LerianStudio/ring · 96 tokens

ring:detecting-goroutine-leaks

Detecting goroutine leaks in Go: greps for goroutine patterns, audits goleak coverage (VerifyTestMain/VerifyNone), runs goleak, and dispatches ring:backend-go to fix leaks and add regression tests. Use after implementation or during review when code spawns goroutines or a leak is suspected. Runs before…

LerianStudio/ring · 109 tokens

ring:test-driven-development

Enforcing the RED-GREEN-REFACTOR loop: write one failing test and watch it fail, write minimal code to pass, then refactor green. Use when starting implementation of a new feature or bugfix, or writing any new production code. Requires pasted failure output as proof of RED; code written before its test must be…

LerianStudio/ring · 89 tokens

ds-debug

Bug hunter — reproduce the failure as an observed red, localize it (bisect, logs, tracing), test at most three hypotheses, land the minimal fix behind a red-proven regression test, and prove it with the project's own check. Use when something is broken and the cause is not yet known.

sungurerdim/dev-skills · 65 tokens