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.
npx agentmods add skills/tercel/spec-forge/propagatenpx skills add tercel/spec-forge --skill propagategit clone --depth 1 https://github.com/tercel/spec-forgeWhat 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 | $0.00072 | $0.04375 |
| Opus 5 | $0.00036 | $0.02188 |
| Sonnet 5 | $0.00014 | $0.00875 |
| Haiku 4.5 | $0.00007 | $0.00438 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Forge — Propagate
⚡ Execution Entry Point (READ THIS FIRST)
Begin executing Step 1 immediately; never fall back to a manual workflow or stop to ask what to do.
Walk a doc change downstream and keep the whole chain consistent.
Iron Law
EVERY UPSTREAM CHANGE PROPAGATES OR FAILS LOUDLY. Partial propagation is worse than no propagation — it creates the illusion of consistency where there is none.
When to Use
- After editing a PRD / SRS / tech-design / feature-spec — find and update every doc that references the changed concepts
- After running
/spec-forge:prdor another generator that modified an existing doc in place - Periodically, with
--since {git-ref}, to catch accumulated drift across recent commits - Before a release, to make sure no doc is silently stale relative to its upstream
- When
spec-forge:analyzeorspec-forge:auditflags inconsistencies between upstream and downstream docs
This skill is the symmetric counterpart to code-forge:fix --review (which propagates code review findings into code changes). Where code-forge:fix walks up from a bug to the spec, spec-forge:propagate walks down from a spec change to the docs and code that depend on it.
Command Format
/spec-forge:propagate [@source-doc.md] [--since git-ref] [--scope all|docs|code] [--dry-run] [--save]
| Argument / Flag | Default | Description |
|---|---|---|
@source-doc.md |
— | The upstream doc whose changes should propagate. If omitted, auto-detect from git diff HEAD (uncommitted changes) or git diff HEAD~1 HEAD (last commit). |
--since {git-ref} |
— | Compute the diff between {git-ref} and HEAD instead of using uncommitted changes. Useful for catching drift across multiple commits. |
--scope |
docs |
What to propagate into. docs = downstream documentation only. code = also flag code that references changed requirement IDs. all = both. |
--dry-run |
off | Generate the impact report and per-downstream proposed changes, but do NOT apply any edits. The user reviews the report and re-runs without --dry-run to apply. |
--save |
off | Save the propagation report to docs/propagate-report-{timestamp}.md in addition to displaying it. |
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.
- 2d ago First seen · 397 lines · 72 tokens per session scan A 344ffd56de87
propagate is a skill published in the GitHub repository tercel/spec-forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 4,375 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 2026-08-31.
Other skills, from other repositories
ppt-design-skill
Design, generate, review, and revise editable PowerPoint presentations through a rigorous brief-to-PNG workflow using the public pptx-designer Python library.
manager
Sync session work into GitHub issues, or query track status across repos. Write: find/update issue + W-label. Read: "что по ". Triggers: "создай issue", "синкни сессию", "manager". Not day/week plans (daily-tasks).
weekly-retro
Use when the user is closing an ISO week, reviewing planned outcomes against evidence, interviewing work Areas, resolving unfinished commitments, or asking for "ретро", "weekly retro", "week review", or lessons from the week.
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
html-draft
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…
pm-metrics
Делает ревью продуктовых метрик — тренды, аномалии, root causes и рекомендации к действиям. Включает декомпозицию North Star (L1/L2), диагностику retention-кривых, анализ воронки, разбор A/B-экспериментов, проверку соответствия OKR и фреймворк атрибуции аномалий. User-invoked only — do NOT auto-trigger. Triggers on…