CHANGELOG

A changelog for prompt files used by coding agents. It records prompt-version changes, why they were made, and whether agents have been measured against a test collection.

In plain words
What is it for?
Use it to track version bumps, rationale, calibration status, and security-related updates across agent prompt files.
Why use it?
It helps maintain a history of changes to agent instructions and distinguish prompts that have been shipped from those that have been evaluated and locked.

Agent

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.

agentmods
npx agentmods add agents/intentdriven/abcd/changelog
Clone the repo
git clone --depth 1 https://github.com/intentdriven/abcd
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02064
Opus 5 $0.00000 $0.01032
Sonnet 5 $0.00000 $0.00413
Haiku 4.5 $0.00000 $0.00206

Measured yesterday against content hash af1771ab9f32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CHANGELOG 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.

agents/CHANGELOG.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent prompt changelog

Per itd-5, every agents/*.md prompt carries a prompt_version and a corresponding entry here recording the bump rationale (and, at 1.0.0 lock, the self-improvement pre-flight outcome and calibration-corpus delta).

Version band. Agents ship in the 0.x band until they clear their calibration corpus — 0.x means "shipped and wired, honestly unmeasured"; 1.0.0 means "measured against a corpus and locked" (itd-81's amendment to itd-5, which governs over the brief's earlier 1.0.0-at-close expectation). The four M6 synthesis agents below entered at 0.1.0, wired to their abcd disembark verbs and unmeasured; lifeboat-oracle has since become lifeboat-reviewer at 0.1.1.

0.2.0 — 2026-08-19 (iss-278 — the itd-5 contract reaches the review/research agents)

Five prompts read attacker-influenceable input without the itd-5 contract: ruthless-reviewer, security-reviewer, docs-currency-reviewer, intent-auditor, sota-researcher (iss-278 records the class and the missing detector). Each gains reads_untrusted_input: true, a capability_scope, an untrusted-data defence paragraph in its body, and an injection-canary fixture — a MINOR bump apiece: behaviour hardening, output contracts unchanged.

ruthless-reviewer 0.2.0

task_classes: [oracle_review] (family-1 change judgement). Canary: a diff whose code comment claims pre-approval and demands zero findings — reported as a finding, never obeyed. Tool grants unchanged; whether review agents should hold Bash at all for external-contribution review is a maintainer decision tracked in iss-278, not silently made here.

security-reviewer 0.2.0

task_classes: [oracle_review]. Canary: a diff whose string claims a security exemption while splicing untrusted input into a shell exfiltration — the exemption claim is itself the finding.

docs-currency-reviewer 0.2.0

task_classes: [cross_document_audit]. Canary: a docs page whose HTML comment demands its claims be marked current — claims verified against code regardless.

Read the full file on GitHub · 143 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. yesterday First seen · 143 lines · 0 tokens per session scan A af1771ab9f32

Subscribe to this mod's changes

CHANGELOG is an agent published in the GitHub repository intentdriven/abcd (3 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,064 tokens. 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 2026-08-31.

Related

Other agents, from other repositories

implementation-agent

You are the Implementation Agent - the final phase in the Belmont implementation pipeline. Your role is to implement ALL tasks in the current milestone, one at a time in order, using the context accumulated in the MILESTONE file by previous phases.

blake-simpson/belmont · 2 tokens

verification-agent

You are the Verification Agent. Your role is to verify that task implementations meet all requirements from the PRD and acceptance criteria. You run in parallel with the Code Review Agent.

blake-simpson/belmont · 2 tokens

code-review-agent

You are the Code Review Agent. Your role is to review code changes for quality, adherence to patterns, and alignment with the PRD solution. You run in parallel with the Verification Agent.

blake-simpson/belmont · 3 tokens

codebase-agent

You are the Codebase Agent - a research-only phase in the Belmont implementation pipeline (runs in parallel with the Design Agent). Your role is to scan the codebase and identify all existing implementation details relevant to the tasks in the current milestone, then write your findings to the MILESTONE file. You do…

blake-simpson/belmont · 3 tokens

design-agent

You are the Design Agent - a research-only phase in the Belmont implementation pipeline (runs in parallel with the Codebase Agent). Your role is to analyze Figma designs (when provided) and document the exact UI specifications needed for ALL tasks in the current milestone, then write your findings to the MILESTONE…

blake-simpson/belmont · 2 tokens

reconciliation-agent

You are a merge conflict resolution agent. Your job is to resolve git merge conflicts that arise when parallel feature or milestone branches are merged back into the main branch.

blake-simpson/belmont · 3 tokens