backfill

backfill is a command for Claude Code from dork-labs/dorkos. It costs 11 tokens per session (843 once invoked), scanned A, original, MIT.

A command that compares commits since a Git tag with the changelog fragments already prepared for release. A Git tag is a named marker for a particular version of the code.

In plain words
What is it for?
Use it before a release to propose one unreleased changelog entry for each missing change, with an optional dry-run or write mode.
Why use it?
It identifies changes that may be missing from the release notes without editing the main changelog.

Command for Claude Code

Part of the flow plugin — 17 skills, 37 commands, 5 agents shipped together

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 commands/dork-labs/dorkos/backfill
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 17 skills, 37 commands, 5 agents.

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 backfill

README.md
[![agentmods](https://agentmods.dev/badge/commands/dork-labs/dorkos/backfill.svg)](https://agentmods.dev/commands/dork-labs/dorkos/backfill)
Your own site
<a href="https://agentmods.dev/commands/dork-labs/dorkos/backfill"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/backfill.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 843 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 $0.00011 $0.00843
Opus 5 $0.00005 $0.00421
Sonnet 5 $0.00002 $0.00169
Haiku 4.5 $0.00001 $0.00084

Measured 3d ago against content hash a1664df292c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backfill 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 3d 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.

.claude/commands/changelog/backfill.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog Backfill

Find commits since the last tag (or a specified tag) that have no fragment yet in changelog/unreleased/, and propose one fragment per missing change. Never edits CHANGELOG.md — only /system:release compiles fragments into it (see changelog/README.md).

Backed by .claude/scripts/changelog_backfill.py (--dry-run / --json / --apply); --apply writes the fragment files.

Arguments

  • $ARGUMENTS - Optional: specific tag to compare from, or --dry-run
    • (no argument) - Compare from latest tag
    • v0.2.0 - Compare from specified tag
    • --dry-run - Show proposed entries without applying

Process

Step 1: Determine Base Tag

# Use argument if provided, otherwise latest tag
TAG="${1:-$(git describe --tags --abbrev=0 2>/dev/null)}"
echo "Comparing from: $TAG"

If no tags exist, report and stop.

Step 2: Get Commits Since Tag

git log $TAG..HEAD --oneline --no-merges

Step 3: Filter and Categorize

Process each commit line:

Include (conventional commit types):

  • feat: / feat(scope): -> Added
  • fix: / fix(scope): -> Fixed
  • refactor: / refactor(scope): -> Changed
  • perf: / perf(scope): -> Changed

Skip (not user-facing):

  • chore: / ci: / test: / docs: / build: / style:

Step 4: Compare with Existing Fragments

Read every fragment in changelog/unreleased/. A commit is covered when a fragment's covers: frontmatter names it (by subject or SHA); a fragment with no declaration falls back to a fuzzy match on key terms. Only propose genuinely missing entries.

Fragments written by --apply declare covers: for the commit they cover, so rewriting their prose for a human never un-covers the commit.

Step 5: Present Proposals

Show proposed entries grouped by category:

## Proposed Changelog Fragments

**Tag**: [tag]
**Commits analyzed**: [count]
**Already covered**: [count]
**New entries proposed**: [count]

### Added

- [user-friendly description] ([sha])

### Changed

- [user-friendly description] ([sha])

### Fixed

- [user-friendly description] ([sha])

Read the full file on GitHub · 109 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. 3d ago First seen · 109 lines · 11 tokens per session scan A a1664df292c3

Subscribe to this mod's changes

backfill is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 843 once invoked, about $0.0001 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 2026-08-31.