Agent skill

Evidence Reconciliation

by TheGoat395 in TheGoat395/Codex-Skills

Resolve stale facts and authority conflicts. An agent skill from TheGoat395/Codex-Skills.

MITAuto-check passedBusiness, Finance & HR

Install Evidence Reconciliation

skills CLI
$ npx skills add TheGoat395/Codex-Skills --skill evidence-reconciliation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheGoat395/Codex-Skills evidence-reconciliation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TheGoat395/Codex-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evidence-reconciliation .claude/skills/evidence-reconciliation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
evidence-reconciliation
GitHub stars
126
Token cost
~1.9k tokens
SKILL.md length
1,040 words
Files
3 (incl. references)
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Resolve stale facts and authority conflicts. An agent skill from TheGoat395/Codex-Skills.

  • Works in 5 steps: the exact claim at issue; → the source that controls it today; → the source that conflicts or appears to… → …
  • Tasks that involve Accounting and bookkeeping
  • SKILL.md covers Outcome, First classify the request, Establish authority before… and Build a claim ledger for…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Evidence Reconciliation is an agent skill from TheGoat395/Codex-Skills. Resolve stale facts and authority conflicts.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/contradiction-protocol.md`).

It sits in Business, Finance & HR, covering Accounting and bookkeeping. The repository describes itself as: Codex-first Agent Skills library for premium frontend, website, motion, accessibility, QA, and handoff workflows. The licence is MIT.

When your agent uses it

  • Tasks that involve Accounting and bookkeeping

Example prompts

  • “/evidence-reconciliation”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. the exact claim at issue;
  2. the source that controls it today;
  3. the source that conflicts or appears to conflict;
  4. whether the difference is factual, temporal, semantic, or a decision change;
  5. the least disruptive correction.

What it can do on your machine

Read from SKILL.md and the folder at commit feff772. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Evidence Reconciliation loads about 1.9k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 17 tokens; SKILL.md has 1,040 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheGoat395/Codex-Skills at commit feff772, republished under its MIT licence (© TheGoat395). 1,040 words, ~1,885 tokens.

Download SKILL.mdSave it as .claude/skills/evidence-reconciliation/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
evidence-reconciliation
description
Resolve stale facts and authority conflicts.

Evidence Reconciliation

Use this skill when a conclusion, plan, document update, vendor comparison, operational rule, price, timeline, limit, or capability depends on a material source conflict, authority ambiguity, stale state or mismatched scope—or when unusually high factual integrity calls for that reconciliation. Multiple consistent sources alone do not require a separate workflow.

Do not use it for simple writing that has no factual or source-conflict component.

Outcome

Produce a conclusion or revision that is traceable to the right source, preserves the existing capability floor, and never turns a related fact into a different fact merely because it supports an appealing answer.

First classify the request

Before answering or editing, separate each material statement into one of these states:

  • Governing current rule — the newest controlling instruction, contract, configuration, or approved decision.
  • Verified current fact — directly observed account, runtime, checkout, source, or official documentation state.
  • Historical source — prior plan, old document, archived observation, or superseded draft.
  • Source-supported interpretation — a conclusion reasonably drawn from evidence.
  • Recommendation — a proposed choice, explicitly not yet adopted.
  • Assumption or unknown — a gap that needs a source, test, or a visible decision.

Never collapse these categories. A trial credit is not automatically a send limit; a vendor marketing capacity is not a chosen operating capacity; a minimum is not a recommended target; an old plan is not the current rule.

For capacity or time claims, record the relevant units, population/system boundary, limiting dimensions, operating assumptions and clock anchor. Apply sender, allowance, trial and warmup dimensions only to commercial/outbound claims, using the capacity/timeline sub-ledger in the protocol. A conclusion must satisfy every applicable limit and prerequisite.

Establish authority before synthesis

For every material conflict, identify:

  1. the exact claim at issue;
  2. the source that controls it today;
  3. the source that conflicts or appears to conflict;
  4. whether the difference is factual, temporal, semantic, or a decision change;
  5. the least disruptive correction.

Within user-owned guidance and subject to higher-priority platform instructions, use this default authority order for operating decisions unless the project defines another. For empirical truth, direct evidence, method, scope and freshness control; user or document authority cannot make a false claim true:

  1. the user's current explicit decision;
  2. newest applicable governing source;
  3. verified current live/account state;
  4. primary official documentation;
  5. validated historical plans and research;
  6. secondary commentary, creator content, remembered context, and marketing claims.

If a newer source is less authoritative, do not silently let recency overrule control.

When a governing source contains both operating policy and dated vendor facts, follow the policy as controlling but recheck the dated vendor fact at an official or authenticated current surface before calling it current.

Build a claim ledger for consequential work

For a wide, high-stakes, or document-revision task, read the contradiction protocol completely and maintain a compact ledger before drafting. The ledger must cover every claim that can change scope, money, capacity, ownership, safety, timeline, outcome, or truthfulness.

Each claim ends in exactly one state: confirmed, conflict unresolved, superseded, proposed, conditional, or unknown. Do not write final language until each material claim has a state.

For commercial capacity, outbound, trial, or deadline claims, also maintain the capacity/timeline sub-ledger in the protocol. Do not combine mutually exclusive operating paths (for example, fresh versus pre-warmed) into one timeline or capacity statement.

Answer without compliance bias

Do not agree just because the user proposes a number, interpretation, or solution. Do not reject it reflexively either.

When the user's statement is correct, say why and cite the controlling evidence. When it is inaccurate, state the exact correction plainly, including whether the error came from a prior assistant response. When evidence is mixed, state the controlling rule and the decision needed to change it.

Use short, direct wording:

The current rule is X. Y is a different metric/source. Z can be proposed later, but it is not established yet.

Never use vague agreement such as “yes, exactly” when the evidence supports only part of the statement.

Show full SKILL.md (382 more words)Show less

Revision discipline

Before revising a standing plan, policy, or operating library:

  1. inventory the affected source documents and their unique jobs; expand to the full library only when the requested revision or its dependencies span it;
  2. map source sections to destination sections;
  3. preserve all useful detail unless a deliberate removal is recorded as superseded, duplicated, wrong, or out of scope;
  4. keep legal, quick-reference, template, and long-form operating documents separate when they have separate use cases;
  5. label future architecture as future rather than silently importing it into current policy;
  6. recheck drift-prone vendor facts at the current official/account surface before including them as operating rules.

A rewrite must preserve or improve useful decision content, exceptions and evidence. Shorter wording is acceptable when it loses no required substance; record source-to-destination mapping for substantive relocation. Do not replace requested complete content with an unrequested summary.

Challenge pass

Before concluding, run these checks:

  • Semantic: Did two similar numbers or terms refer to different things?
  • Temporal: Is an older fact being used as current state?
  • Authority: Did a noncontrolling source override the governing one?
  • Scope: Did a proposed future capability become a current promise?
  • Economics: Did a vendor price, usage charge, labor cost, or client-owned cost disappear?
  • Lifecycle/timeline: Does the claimed date name its clock anchor and satisfy applicable dependencies? For outbound/commercial capacity, include trial expiry, upgrade, authentication, warmup, ramp and reply-operation gates only where relevant.
  • Ownership: Did the revision weaken client control, isolation, recovery, or handoff?
  • Completeness: Did any document, source, exception, or user requirement get silently dropped?
  • Truth: Does every strong claim have direct evidence at the claimed verification layer?

Repair the issue or label it unresolved. Do not move forward by averaging the conflicting claims.

Report with a source map

For material work, report:

  1. the controlling conclusion;
  2. exact corrections and their source class;
  3. documents/systems changed or intentionally retained;
  4. unverified or approval-gated items;
  5. the source-to-output mapping for any rewritten library.

Do not claim a source was read, a condition was verified, or a conflict was resolved unless that happened.

Instruction authority sets objectives and operating rules; it does not establish empirical truth. Evaluate factual claims using direct evidence, method, source quality, scope and freshness even when a claim comes from the user or a governing file.

© TheGoat395, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/evidence-reconciliation of TheGoat395/Codex-Skills.

  • SKILL.md
  • agents/openai.yaml
  • references/contradiction-protocol.md

Open the folder on GitHubat commit feff772

Compare with similar skills

Evidence Reconciliation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Evidence Reconciliation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Evidence Reconciliation this skillTheGoat395/Codex-Skills126—~1.9kAutomated safety check: PassMIT
Sync Upstreamnyaruka/phonenumbers1.6k—~2.8kAutomated safety check: PassMIT
Radiology Tablehuang-sir1/radiology-skills1.9k—~1.3kAutomated safety check: PassCustom licence
ERPClaw ERP Controlleravansaber/erpclaw116—~18kAutomated safety check: PassGPL-3.0
Odoo Agency Fleet Reviewerpipe-org/mcp-odoo421—~699Automated safety check: PassMIT
Beancount Closebex-co/beancount-io297—~1.4kAutomated safety check: PassMIT

Similar skills

  • Sync Upstream

    nyaruka/phonenumbers

    Sync this Go port with a new upstream google/libphonenumber release — regenerate the embedded metadata and reconcile the ported Java logic.

    1.6k GitHub stars~2.8k tokensUpdated 8 days ago
    Business, Finance & HRAuto-check passed
  • Radiology Table

    huang-sir1/radiology-skills

    Create/audit editable publication tables with source reconciliation; not figures or statistical inference.

    1.9k GitHub stars~1.3k tokensUpdated 20 days ago
    Business, Finance & HRAuto-check passed
  • ERPClaw ERP Controller

    avansaber/erpclaw

    Operates the ERPClaw self-hosted ERP in plain language: accounting, invoicing, inventory, purchasing, tax, HR, payroll and reports, treating the ERP as the single source of truth.

    116 GitHub stars~18k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Odoo Agency Fleet Review

    erpipe-org/mcp-odoo

    Review many client Odoo databases at once through odoo-mcp's cross-instance tools — fleet-wide accounting health, per-client aging, partial-failure triage — for agencies and partners managing 5–50…

    421 GitHub stars~699 tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Beancount Close

    bex-co/beancount-io

    Close an accounting period in a Beancount ledger by reconciling each active account through beancount-reconcile, checking assertions and recurring gaps, reviewing flags, then proposing a commit with…

    297 GitHub stars~1.4k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Forward Implementation First

    Vuk97/forward-implementation-first

    Keeps an agent building and validating real output instead of servicing its own bookkeeping.

    176 GitHub stars~1.8k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed

More from TheGoat395/Codex-Skills

All 23 skills in this repo
  • Premium Visual Reference Library

    TheGoat395/Codex-Skills

    Find references, Viktor Oddy and MotionSites. An agent skill from TheGoat395/Codex-Skills.

    126 GitHub stars~867 tokensUpdated 1 mo ago
    Auto-check passed
  • Agent Evaluation Operations

    TheGoat395/Codex-Skills

    Evaluate agent and skill behavior or routing. An agent skill from TheGoat395/Codex-Skills.

    126 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Creativity

    TheGoat395/Codex-Skills

    Generate original ideas or escape fixation. An agent skill from TheGoat395/Codex-Skills.

    126 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Final Client Handoff

    TheGoat395/Codex-Skills

    Prepare verified ownership and delivery notes. An agent skill from TheGoat395/Codex-Skills.

    126 GitHub stars~477 tokensUpdated 1 mo ago
    Auto-check passed
  • Visual Regression Lab

    TheGoat395/Codex-Skills

    Compare captures; stitch lazy/animated pages. An agent skill from TheGoat395/Codex-Skills.

    126 GitHub stars~516 tokensUpdated 1 mo ago
    Auto-check passed
  • Web Reference Research

    TheGoat395/Codex-Skills

    Analyze selected sources: Viktor or MotionSites. An agent skill from TheGoat395/Codex-Skills.

    126 GitHub stars~475 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Evidence Reconciliation

What does Evidence Reconciliation do?

Resolve stale facts and authority conflicts. An agent skill from TheGoat395/Codex-Skills. Evidence Reconciliation is an agent skill from TheGoat395/Codex-Skills. Resolve stale facts and authority conflicts.

When should I use Evidence Reconciliation?

Evidence Reconciliation fits situations like: tasks that involve Accounting and bookkeeping.

How do I install Evidence Reconciliation in Claude Code?

Run `npx skills add TheGoat395/Codex-Skills --skill evidence-reconciliation -a claude-code`. Or copy the skill folder (skills/evidence-reconciliation in TheGoat395/Codex-Skills) into .claude/skills/evidence-reconciliation in your project. Claude Code loads it when a task matches its description.

How do I install Evidence Reconciliation in Codex?

Run `npx skills add TheGoat395/Codex-Skills --skill evidence-reconciliation -a codex`. Or copy the skill folder (skills/evidence-reconciliation in TheGoat395/Codex-Skills) into .agents/skills/evidence-reconciliation in your project. Codex loads it when a task matches its description.

Can I use Evidence Reconciliation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheGoat395/Codex-Skills --skill evidence-reconciliation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evidence-reconciliation, .gemini/skills/evidence-reconciliation, .github/skills/evidence-reconciliation and .opencode/skills/evidence-reconciliation in your project.

What does Evidence Reconciliation need to run?

SKILL.md names no scripts, command-line tools or credentials: Evidence Reconciliation is instructions for the agent only.

Does Evidence Reconciliation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Evidence Reconciliation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Evidence Reconciliation use?

Evidence Reconciliation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Evidence Reconciliation use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1k tokens, read only when the agent opens those files.

What are the alternatives to Evidence Reconciliation?

Skills that share tags, products or a category with Evidence Reconciliation: Sync Upstream (nyaruka/phonenumbers, 1.6k stars), Radiology Table (huang-sir1/radiology-skills, 1.9k stars), ERPClaw ERP Controller (avansaber/erpclaw, 116 stars) and Odoo Agency Fleet Review (erpipe-org/mcp-odoo, 421 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evidence Reconciliation?

TheGoat395 (a GitHub user) maintains it in TheGoat395/Codex-Skills, which has 126 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on September 11, 2026.

Source: TheGoat395/Codex-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.