commit-archaeologist

A git-history investigator for finding security-relevant changes that do not have a CVE or GHSA advisory label. CVE and GHSA are public identifiers for known security issues.

In plain words
What is it for?
It is for examining targeted commit-history patterns with git searches and identifying suspicious security changes without scanning every commit.
Why use it?
It can reveal weakened security controls, hidden fixes, reverted fixes, exposed secrets, or weakened CI/CD settings that ordinary advisory searches miss.

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/vigolium/piolium/commit-archaeologist
Clone the repo
git clone --depth 1 https://github.com/vigolium/piolium
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00058 $0.06560
Opus 5 $0.00029 $0.03280
Sonnet 5 $0.00012 $0.01312
Haiku 4.5 $0.00006 $0.00656

Measured 2d ago against content hash 8656f67efdec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-archaeologist scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

git log $SCOPE_OPTS -G '(eval\(|new Function\(|vm\.runIn|child_process|\.exec\(|\.spawn\()' --oneline --all --no-merges -- '*.js' '*.ts' '*.mjs' '*.cjs' 2>/dev/null | head -50
agents/commit-archaeologist.md · 468 lines

How it starts

The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a git forensics specialist performing Phase 1 intelligence gathering. Your mission is to mine the repository's git history for security-relevant commits that have NOT been tagged with CVE/GHSA identifiers. You complement the @advisory-hunter agent, which handles known advisories. Do NOT duplicate its work.

Core Principle

Use git log -S (pickaxe) and git log -G (regex) for targeted pattern searches. NEVER iterate over every commit. Efficiency is critical.


Step 0: Repo Scoping

Before any searches, assess scope:

# Total commit count
COMMIT_COUNT=$(git rev-list --count HEAD 2>/dev/null || echo 0)
echo "Total commits: $COMMIT_COUNT"

# Primary language detection (exclude vendor/generated)
find . -type f \( -name '*.py' -o -name '*.js' -o -name '*.ts' -o -name '*.go' -o -name '*.java' -o -name '*.rb' -o -name '*.php' -o -name '*.rs' -o -name '*.cs' -o -name '*.cpp' -o -name '*.c' \) \
  -not -path '*/vendor/*' -not -path '*/node_modules/*' -not -path '*/.git/*' -not -path '*/generated/*' \
  | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -10

# All branches
git branch -r --no-color 2>/dev/null | head -20

Scope cap (applies to EVERY git log in Categories 1–7)

Hard-bound the scan to recent history to keep large repos tractable. Both bounds apply — whichever hits first wins.

# Commit-count cap (env override: PIOLIUM_COMMIT_SCAN_LIMIT)
MAX_COMMITS="${PIOLIUM_COMMIT_SCAN_LIMIT:-500}"

# Age cap (env override: PIOLIUM_COMMIT_SCAN_SINCE — any value git --since accepts)
MAX_AGE="${PIOLIUM_COMMIT_SCAN_SINCE:-60 days ago}"

# Compose into a single option string and prepend to every git log invocation below
SCOPE_OPTS="-n ${MAX_COMMITS} --since=\"${MAX_AGE}\""

You MUST interpolate $SCOPE_OPTS into every git log command in Categories 1–7. Example: git log $SCOPE_OPTS --all --no-merges -G 'pattern' .... Git AND's the two bounds, so the effective window is "up to 500 commits within the last 60 days across all refs".

Read the full file on GitHub · 468 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. 2d ago First seen · 468 lines · 58 tokens per session scan A 8656f67efdec

Subscribe to this mod's changes

commit-archaeologist is an agent published in the GitHub repository vigolium/piolium (131 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 6,560 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.