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 skills add michal-bajer1/shadow --skill backfillgit clone --depth 1 https://github.com/michal-bajer1/shadowWrote 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.
[](https://agentmods.dev/skills/michal-bajer1/shadow/backfill)<a href="https://agentmods.dev/skills/michal-bajer1/shadow/backfill"><img src="https://agentmods.dev/badge/skills/michal-bajer1/shadow/backfill.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.02198 |
| Opus 5 | $0.00015 | $0.01099 |
| Sonnet 5 | $0.00006 | $0.00440 |
| Haiku 4.5 | $0.00003 | $0.00220 |
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 7d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backfill decision records from existing documentation into .shadow/. Work
through four phases in order: discover, deduplicate, triage, interview and record.
Phase 1 — Discover decision documents
Search the repo for files that are likely to contain recorded decisions.
Path patterns to scan (check all that exist):
docs/adr/ adr/ decisions/
docs/decisions/ architecture/ design/
docs/architecture/
Filename patterns (case-insensitive, anywhere in the tree):
*ADR* *DECISION* *ARCHITECTURE* *RFC* *DESIGN*
NNN-*.md (numbered decision records) *.adr.md
Content patterns — files not matching the above but containing any of:
## Decision ## Rationale ## Context and Problem Statement
## Status ## Considered Options ## Why
Run:
# Path/filename scan
find . \( -path ./.git -o -path ./.shadow -o -path ./node_modules \) -prune \
-o -type f -iname "*adr*" -print \
-o -type f -iname "*decision*" -print \
-o -type f -iname "*architecture*" -print \
-o -type f -name "[0-9][0-9][0-9][0-9]-*.md" -print
# Heading scan for remaining .md files
grep -rl "## Decision\|## Rationale\|## Considered Options\|## Why" \
--include="*.md" . \
| grep -v ".git\|.shadow\|node_modules"
Deduplicate the combined list. Read each file briefly (title + first 40 lines) to confirm it contains a real decision and is not purely descriptive.
If the user passed a path argument (e.g. /shadow:backfill src/payments), limit
discovery to that subtree.
Phase 2 — Check existing shadow coverage
For each candidate document, infer the target code area — the module or directory the decision is about, not where the doc file lives.
Signals to look for inside the doc:
- File paths or directories mentioned explicitly
- Service or module names that map to directories in the repo
- The ADR title (e.g. "Use PostgreSQL for the jobs queue" → look for
jobs/,queue/,worker/directories)
Verify that the inferred path exists in the repo:
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.
- 7d ago First seen · 250 lines · 31 tokens per session scan A 0d80e5c42d81
backfill is a skill published in the GitHub repository michal-bajer1/shadow (2 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 2,198 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…