propagate

A command for carrying changes from an edited software document to other documents that depend on it. Documents such as product requirements, system requirements, and technical designs form a connected chain.

In plain words
What is it for?
Use it after editing an upstream document to find affected downstream documents and update them, with options to limit the work to documentation, code, or both.
Why use it?
It helps prevent related documentation from becoming inconsistent after one document changes.

Command

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/tercel/spec-forge/propagate
Clone the repo
git clone --depth 1 https://github.com/tercel/spec-forge
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 748 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 $0.00030 $0.00748
Opus 5 $0.00015 $0.00374
Sonnet 5 $0.00006 $0.00150
Haiku 4.5 $0.00003 $0.00075

Measured yesterday against content hash 5f9f2105584b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

propagate 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.

commands/propagate.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior technical writer responsible for keeping a project's documentation chain coherent. When an upstream document changes, every downstream document that references the changed concepts must be updated, or the chain loses the team's trust.

Your task is to propagate changes for: $ARGUMENTS

Workflow

Step 1: Determine Source

Parse $ARGUMENTS for the source document(s) and flags:

  • If @source-doc.md is provided, that is the source.
  • If --since {git-ref} is provided, the source is all .md files changed between that ref and HEAD.
  • Otherwise, auto-detect from git status (uncommitted) or git diff HEAD~1 HEAD (last commit).

If no source can be detected, display:

No doc changes detected. Provide an explicit @source-doc.md or use --since {ref}.

and stop.

Step 2: Launch Propagate

Launch Agent(subagent_type="general-purpose") with the following prompt:


You are responsible for propagating documentation changes from an upstream spec downstream through the doc chain.

Source documents: {resolved source files} Scope: {docs|code|all — default docs} Mode: {normal|dry-run}

Read the propagate skill definition at: skills/propagate/SKILL.md

Follow every step of the workflow exactly:

  1. Step 1 (Determine Source) is already done — use the resolved sources above.
  2. Continue from Step 2 (Extract Changed Concepts via sub-agent).
  3. Step 3 (Discover Downstream References via sub-agent).
  4. Step 4 (Per-Downstream Impact Analysis — parallel sub-agents, max 8 at a time).
  5. Step 5 (Interactive Review — use AskUserQuestion for each downstream file with proposed changes).
  6. Step 6 (Apply Changes — surgical Edit only, never Write, never rewrite).
  7. Step 7 (Verify — re-grep for stale references, run tests if scope includes code).
  8. Step 8 (Report — display the propagation summary).

Key rules:

  • Never modify the source documents themselves — they are the upstream truth.
  • Never use Write to overwrite a downstream file — use Edit for surgical changes.
  • Never auto-apply LOW-confidence or AMBIGUOUS changes — ask the user.
  • Never touch code files when scope = docs.
  • If --dry-run is set, generate the full report but apply nothing.
  • Surface every stale reference that survives the propagation as a STILL_STALE warning.

Read the full file on GitHub · 74 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 · 74 lines · 30 tokens per session scan A 5f9f2105584b

Subscribe to this mod's changes

propagate is a command published in the GitHub repository tercel/spec-forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 748 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 2026-08-31.