reflect-digest

reflect-digest is a skill for Claude Code, Codex from runxhq/runx. It costs 46 tokens per session (469 once invoked), scanned A, original, Apache-2.0.

An internal review stage that groups repeated run signals by skill and turns well-supported patterns into bounded improvement proposals.

In plain words
What is it for?
It reads stored reflection records, applies confidence and support thresholds, proposes at most one improvement per skill, and hands validated proposals to a later improvement process.
Why use it?
It prevents isolated or weak evidence from triggering changes, while keeping proposed improvements tied to the runs that support them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It reads stored reflection records, applies confidence and support thresholds, proposes at most one improvement per skill, and hands validated proposals to a later improvement process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/reflect-digest
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 runxhq/runx --skill reflect-digest
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

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-digest

README.md
[![agentmods](https://agentmods.dev/badge/skills/runxhq/runx/reflect-digest/github.svg)](https://agentmods.dev/skills/runxhq/runx/reflect-digest)
Your own site
<a href="https://agentmods.dev/skills/runxhq/runx/reflect-digest"><img src="https://agentmods.dev/badge/skills/runxhq/runx/reflect-digest/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.

agentmods 80×15 button for reflect-digest

Your own site · 80×15
<a href="https://agentmods.dev/skills/runxhq/runx/reflect-digest"><img src="https://agentmods.dev/badge/skills/runxhq/runx/reflect-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 469 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 $0.00046 $0.00469
Opus 5 $0.00023 $0.00234
Sonnet 5 $0.00009 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 8d ago against content hash d5157d4d018f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reflect-digest 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.

The scan reads SKILL.md. This mod also ships 1 executable file (reflect-digest.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/reflect-digest/SKILL.md · 53 lines

What it actually says

Reflect Digest

Turn repeated post-run reflection signals into bounded improvement work without re-diagnosing one receipt or drafting a parallel pull-request artifact.

The graph reads durable reflect events through data-store, admits explicit replay projections when supplied, applies deterministic confidence and support floors, then asks one bounded agent act to describe at most one improvement per skill. A final deterministic step verifies every cited receipt belongs to that skill's group and emits a skill-lab improve handoff.

The skill does not write a package, open a pull request, publish, or invoke the mutating improvement runner. The handoff preserves the target, objective, receipt evidence, and non-goals for later governed execution.

Composes

  • data-store#list_stream_heads

Inputs

  • reflect_projections: explicit projections for replay; otherwise durable state is read from data_source_ref and state_resource.
  • skill_filter, since: optional read bounds.
  • min_support: minimum number of admitted projections for one skill.
  • min_confidence: minimum confidence for each admitted projection.

Outputs

  • proposals: validated skill-specific improvement opportunities.
  • skill_lab_handoffs: executable request packets naming skill-lab, runner improve, target directory, objective, primary receipt, evidence summary, and supporting receipt ids.

Agent task contracts

reflect-digest

Review each grouped reflection independently. Return at most one proposal per skill_ref, and return an empty proposals array when no group supports a bounded fix. Every proposal must contain skill_ref, repo-relative target_dir, objective, evidence_summary, supporting_receipt_ids, and boundaries. Receipt ids must come from that group. Do not diagnose a single run again, author code, draft a pull request, publish, or mutate the target package.

Files

What ships with it

2 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.

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 · 53 lines · 46 tokens per session scan A d5157d4d018f

Subscribe to this mod's changes

reflect-digest is a skill published in the GitHub repository runxhq/runx (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 46 tokens to every session and 469 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.