reflect

reflect is a skill for Claude Code, Codex from znlgis/my-opencode-deepseek-config. It costs 60 tokens per session (655 once invoked), scanned A, original, MIT.

A review loop for finding repeated problems in an OpenCode setup and suggesting small configuration improvements. It looks at recent sessions, rules, skills, routing, and commands.

In plain words
What is it for?
Use it to review agent failures, missing or misused skills, broken workflows, ignored rules, command issues, and repeated unnecessary work.
Why use it?
It helps turn recurring mistakes or wasted effort into lasting setup changes instead of fixing the same problem each time.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md; mentions OpenCode.

Good fit Use it to review agent failures, missing or misused skills, broken workflows, ignored rules, command issues, and repeated unnecessary work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/znlgis/my-opencode-deepseek-config/reflect
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 znlgis/my-opencode-deepseek-config --skill reflect
Clone the repo
git clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-config

Made for: Claude Code, Codex.

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 reflect

README.md
[![agentmods](https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/reflect.svg)](https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/reflect)
Your own site
<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/reflect"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/reflect.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 655 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00655
Opus 5 $0.00030 $0.00328
Sonnet 5 $0.00012 $0.00131
Haiku 4.5 $0.00006 $0.00065

Measured 8d ago against content hash 095ea639a06a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reflect 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.

opencode/skills/reflect/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflect

A lightweight continuous-improvement loop for the opencode configuration. After enough sessions, patterns emerge: the orchestrator routes wrong, a skill is incomplete, a rule is ignored, a workflow is missing. Reflect surfaces these and proposes minimal fixes.

When to use

  • The user says "reflect on our sessions" or "review the config"
  • You notice the same friction in 3+ sessions (same agent fails, same skill loaded but misused, same rule violated)
  • After a major config change — check that nothing broke

Workflow

Step 1: Gather signals

Review what's available from the current session and recent history:

  1. What agents were dispatched? Any failures or escalations?
  2. What skills were loaded? Were any requested but missing?
  3. What AGENTS.md rules were violated or misunderstood?
  4. What commands were used? Any templating issues?
  5. Were there unnecessary token burns (large file reads that should've been explored, sequential reads that could've been parallel)?

Step 2: Identify patterns

Look for low-cost, high-impact fixes:

Signal Possible Fix
Flash agent escalates to pro 3+ times for same category Adjust agent description or routing rules
Skill triggered but agent ignores it Skill description too vague — add trigger keywords
Repeated style violations Add explicit rule to AGENTS.md or agent prompt
Agent keeps trying to delegate when it shouldn't Add "no delegation" constraint to that agent
Sequential reads where parallel would work Not a config fix — note in report as behavioral
Large diffs overwhelm reviewer Threshold in code-review skill may be too high

Step 3: Propose changes

Present findings as a checklist:

## Reflect findings

### Patterns found
- [pattern]: [evidence in N sessions]

### Proposed changes
1. [change to file]: [why]
2. [change to file]: [why]

### Token savings estimate
- [N tokens saved per session by each change]

### NOT recommended
- [idea]: [why it's wrong or too expensive]

Read the full file on GitHub · 79 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.

  1. 8d ago First seen · 79 lines · 60 tokens per session scan A 095ea639a06a

Subscribe to this mod's changes

reflect is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 655 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.