secrets

secrets is a skill for Claude Code from kalpmodi/akira. It costs 67 tokens per session (6,268 once invoked), scanned A, original, MIT.

A penetration-testing workflow for looking for exposed secrets such as API keys, access tokens, and credentials across a target's files and services.

In plain words
What is it for?
It is for checking JavaScript bundles, code repositories and their history, Postman collections, API specifications, environment files, and cloud configuration files.
Why use it?
It focuses the search on assets discovered during reconnaissance, helping avoid broad scans that miss relevant locations or produce unrelated results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; positional $N argument.

Part of the akira plugin — 16 skills 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 skills/kalpmodi/akira/secrets
Any agent
npx skills add kalpmodi/akira --skill secrets
Clone the repo
git clone --depth 1 https://github.com/kalpmodi/akira

Made for: Claude Code.

Or install akira, the plugin that ships this one along with the rest of its 16 skills.

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 secrets

README.md
[![agentmods](https://agentmods.dev/badge/skills/kalpmodi/akira/secrets.svg)](https://agentmods.dev/skills/kalpmodi/akira/secrets)
Your own site
<a href="https://agentmods.dev/skills/kalpmodi/akira/secrets"><img src="https://agentmods.dev/badge/skills/kalpmodi/akira/secrets.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,268 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 5.1 $0.00067 $0.06268
Opus 5 $0.00034 $0.03134
Sonnet 5 $0.00013 $0.01254
Haiku 4.5 $0.00007 $0.00627

Measured 6d ago against content hash 9b0a414f4a06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

secrets 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sk "$URL" -o "$RESULTS/secrets/js-bundles/$FILENAME" 2>/dev/null
skills/secrets/SKILL.md · 490 lines

How it starts

The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Secrets Hunting Phase

Overview

Hunts credentials across every surface the target has ever touched: JS bundles, GitHub repos, deleted commits, Postman collections, API specs, .env files, cloud configs.

This phase does NOT run generically. It reads exactly what recon found and targets THOSE specific assets. TruffleHog runs on the actual JS bundle URLs from recon, not on the domain name.

See references/intelligence-protocol.md for the full coordination contract.


Phase 0: Smart Intake (Run Before Any Tool)

source ~/.claude/skills/_shared/phase0.sh
source ~/.claude/skills/_shared/signals.sh

p0_init_vars "$1"
p0_state_gate "HARVEST" || exit 0
p0_read_relay recon
p0_read_memory
p0_read_hypotheses

echo "=== SECRETS SMART INTAKE: $TARGET ==="
echo "State: $STATE | Top hypothesis: $TOP_HYPO_LABEL [$TOP_HYPO_PROB%]"
echo "JS bundles to scan: $(echo "$JS_BUNDLES" | wc -l | tr -d ' ')"
echo "GitHub orgs found: $(echo "$GITHUB_ORGS" | tr ' ' '\n' | wc -l | tr -d ' ')"
echo "Live hosts: $(echo "$LIVE_HOSTS" | wc -l | tr -d ' ')"
echo "AWS mode: $AWS_HINT | WAF: $WAF"
echo "ATW flagged (will skip): $ATW_FLAGGED"
echo ""

Phase 1: Build Execution Manifest

Generate the manifest BEFORE running a single tool. Write it to session.json. Every MUST item MUST complete before this phase ends.

# Build manifest items dynamically from smart intake
MANIFEST_ITEMS="[]"

# M01: TruffleHog on discovered JS bundles (MUST if bundles found)
[ -n "$JS_BUNDLES" ] && MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m01","tool":"trufflehog","target":"js_bundles","reason":"JS bundles found in recon - primary secret surface","priority":"MUST","status":"pending"}]')

# M02: TruffleHog on GitHub org (MUST if org found)
[ -n "$GITHUB_ORGS" ] && MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m02","tool":"trufflehog_github","target":"github_org","reason":"GitHub org identified in recon","priority":"MUST","status":"pending"}]')

# M03: Gitleaks on downloaded repos (SHOULD)
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m03","tool":"gitleaks","target":"github_repos","reason":"Regex-based detection catches patterns TruffleHog misses","priority":"SHOULD","status":"pending"}]')

# M04: Postman collection hunting (MUST - often missed, high value)
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m04","tool":"postman_hunt","target":"postman.com","reason":"Postman collections often contain API keys + internal endpoints","priority":"MUST","status":"pending"}]')

# M05: API spec hunting on all live hosts (MUST)
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m05","tool":"swagger_hunt","target":"live_hosts","reason":"Exposed API specs reveal all endpoints including auth-required ones","priority":"MUST","status":"pending"}]')

# M06: .env / config file hunting (MUST)
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m06","tool":"env_hunt","target":"live_hosts","reason":"Accidentally exposed config files","priority":"MUST","status":"pending"}]')

# M07: AWS-specific hunting (MUST if AWS hint)
[ "$AWS_HINT" = "true" ] && MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m07","tool":"trufflehog_aws","target":"all_surfaces","reason":"AWS detected in tech stack - hunt AKIA/ASIA keys specifically","priority":"MUST","status":"pending"}]')

# M08: GitHub dorking (SHOULD)
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m08","tool":"github_dorking","target":"github.com","reason":"Manual dorks find what automated scans miss","priority":"SHOULD","status":"pending"}]')

# M09: Wayback/Archive secret hunting (SHOULD - old JS versions)
MANIFEST_ITEMS=$(echo $MANIFEST_ITEMS | jq '. + [{"id":"m09","tool":"wayback_js","target":"archived_js","reason":"Old JS versions often contain deleted-but-committed secrets","priority":"SHOULD","status":"pending"}]')

# Write manifest to session.json
jq --argjson items "$MANIFEST_ITEMS" \
  '.scalpel.active_manifest = {"phase":"secrets","generated_at":"'"$(date '+%Y-%m-%d %H:%M')"'","items":$items}' \
  $SESSION > /tmp/s.json && mv /tmp/s.json $SESSION

echo "=== EXECUTION MANIFEST GENERATED ==="
jq '.scalpel.active_manifest.items[] | "[\(.priority)] \(.id): \(.tool) on \(.target)"' $SESSION
echo ""

Read the full file on GitHub · 490 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. 6d ago First seen · 490 lines · 67 tokens per session scan A 9b0a414f4a06

Subscribe to this mod's changes

secrets is a skill published in the GitHub repository kalpmodi/akira (21 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 6,268 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

performing-cloud-penetration-testing-with-pacu

Performing authorized AWS penetration testing using Pacu, the open-source AWS exploitation framework, to enumerate IAM configurations, discover privilege escalation paths, test credential harvesting, and validate security controls through systematic attack simulation.

xalgorix/xalgorix · 51 tokens

conducting-cloud-penetration-testing

This skill outlines methodologies for performing authorized penetration testing against AWS, Azure, and GCP cloud environments. It covers understanding the shared responsibility model for testing scope, leveraging cloud-specific attack tools like Pacu and ScoutSuite, exploiting IAM misconfigurations, testing for SSRF…

xalgorix/xalgorix · 79 tokens

performing-kubernetes-penetration-testing

Kubernetes penetration testing systematically evaluates cluster security by simulating attacker techniques against the API server, kubelet, etcd, pods, RBAC, network policies, and secrets. Using tools.

xalgorix/xalgorix · 46 tokens

conducting-full-scope-red-team-engagement

Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities.

26zl/cybersec-toolkit · 44 tokens

llm-prompt-injection

Use when testing an authorized LLM application for prompt injection, system-prompt exposure, unsafe tool use, or RAG data-boundary failures.

uphiago/recon-skills · 36 tokens

conducting-cloud-penetration-testing

This skill outlines methodologies for performing authorized penetration testing against AWS, Azure, and GCP cloud environments. It covers understanding the shared responsibility model for testing scope, leveraging cloud-specific attack tools like Pacu and ScoutSuite, exploiting IAM misconfigurations, testing for SSRF…

26zl/cybersec-toolkit · 79 tokens