What is issue-root-resolution?

A root-cause workflow for resolving a group of related software issues. It traces each issue to the mechanism that allows it, then requires evidence that the fix works.

Use it to investigate issue clusters, map their causes, plan deletion-first fixes, and verify closure.

It prevents teams from applying separate symptom fixes while leaving the shared underlying problem intact.

How susomejias/rembric configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to susomejias/rembric. 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/susomejias/rembric/main/.agents/skills/issue-root-resolution/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/susomejias/rembric

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/susomejias/rembric/issue-root-resolution/github.svg)](https://agentmods.dev/skills/susomejias/rembric/issue-root-resolution)

Your own site

<a href="https://agentmods.dev/skills/susomejias/rembric/issue-root-resolution"><img src="https://agentmods.dev/badge/skills/susomejias/rembric/issue-root-resolution/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/susomejias/rembric/issue-root-resolution"><img src="https://agentmods.dev/badge/skills/susomejias/rembric/issue-root-resolution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,215 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.

Model	Per session	Once invoked
Fable 5.1	$0.00080	$0.01215
Opus 5	$0.00040	$0.00607
Sonnet 5	$0.00016	$0.00243
Haiku 4.5	$0.00008	$0.00121

Measured 9d ago against content hash 90253c98ce7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

issue-root-resolution 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 9d 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.

.agents/skills/issue-root-resolution/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Root Resolution

A cluster is resolved when the mechanism that permits it is removed or guarded at the correct boundary, each affected report has executable evidence, and the implementation remains faithful to Rembric's specifications and invariants. Do not turn a cluster into a collection of symptom patches.

1. Establish the current mechanism

Work from current origin/main, not an issue's historical description.

Read full issue bodies, comments, linked PRs, and relevant OpenSpec specs.
Reproduce every candidate root through a real caller boundary; include a passing control in the same run.
Make a read-only mechanism map before editing. Every claim gets a file:line anchor and explains what happens today, not what the issue says should happen.
Record report date and the commit/release being tested. A pre-fix report is not evidence that the current build remains broken.

If the map contradicts the report, say so. The symptom may be valid while the proposed mechanism is wrong; strengthen the repro until it distinguishes them.

2. Shape the smallest root fix

Rank alternatives in this order:

remove the mechanism, making the whole class impossible;
add a static/invariant guard that makes reintroduction fail;
apply a local predicate fix behind a failing real-surface reproduction;
only when evidence rules out the above, add a new state, flag, command, compatibility path, or other lasting surface.

For every option that adds surface, explain why a deletion/relaxation shape cannot work. Do not add a parallel representation of truth: memory lifecycle, project scope, and topic convergence already have authoritative locations.

Apply these Rembric constraints while designing:

Scope is resolved at the service layer. New MCP tools use resolveEffectiveScope; handlers do not construct scopes or infer a default.
Append-only data remains append-only: do not DELETE memory rows or update content to correct a defect. Use existing lifecycle/replacement semantics.
SQL belongs in src/db/, services own transactions, and scoped repository methods require Scope.
A behavioural change, new MCP tool, or invariant change needs an OpenSpec change before implementation. Table-rebuild migrations rely on the runner's FK-safety dance; do not reproduce it ad hoc in a migration.
Plugin work must preserve one shared implementation across five clients; read rembric-plugin-development before changing apps/plugin/.

Read the full file on GitHub · 120 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.

9d ago First seen · 120 lines · 80 tokens per session scan A 90253c98ce7b

Subscribe to this mod's changes

issue-root-resolution is a skill published in the GitHub repository susomejias/rembric (12 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 1,215 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 2026-08-30.

Claude Code Debugging agent-memory codex-cli hermes-agent mcp nodejs

debug-task

Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…

moonrepo/moon · 231 tokens

node-inspect-debugger

Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

mateaix/mateclaw · 19 tokens

hunt-nodejs

Hunt Node.js specific vulnerabilities — Prototype Pollution → RCE chains (lodash/merge/assign), Express trust proxy misconfiguration, childprocess/eval injection, template engine SSTI (EJS/Pug/Handlebars), path traversal in file servers, require() injection, environment variable exfil via /proc/self/environ. Use when…

uphiago/recon-skills · 87 tokens

rembric: Skill for Claude Code