Borrowing it
Nothing to install: this file belongs to dfirtnt/Huntable-CTI-Studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dfirtnt/Huntable-CTI-Studio/main/.claude/skills/source-healing/SKILL.mdgit clone --depth 1 https://github.com/dfirtnt/Huntable-CTI-StudioWrote 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/dfirtnt/huntable-cti-studio/source-healing)<a href="https://agentmods.dev/skills/dfirtnt/huntable-cti-studio/source-healing"><img src="https://agentmods.dev/badge/skills/dfirtnt/huntable-cti-studio/source-healing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dfirtnt/huntable-cti-studio/source-healing"><img src="https://agentmods.dev/badge/skills/dfirtnt/huntable-cti-studio/source-healing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00155 | $0.02415 |
| Opus 5 | $0.00077 | $0.01208 |
| Sonnet 5 | $0.00031 | $0.00483 |
| Haiku 4.5 | $0.00015 | $0.00242 |
Grade A, and why
source-healing 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 11d 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.
Run them with `curl` / web fetch directly; you are the diagnostic engine, so no How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Healing
A guided workflow to find why a CTI source stopped collecting and fix it
safely. You (Claude) are the diagnostic engine: you run probes, apply the
playbook in references/playbook.md, and propose one concrete fix. A human
approves every change.
Why this is a skill and not a background job
An automated version of this existed (Celery loop + headless LLM mutating live configs) and was removed because unattended config mutation was not production-safe. The valuable part — the probes and the symptom→fix playbook — is pure knowledge and lives on here. The safety comes from the delivery vehicle: an operator runs this, sees the diagnosis, and approves the fix. Keep that property. Do not add scheduling, auto-apply, or batch-without-confirm.
Operating rules (read before touching anything)
These exist because a source config is live production state and the fixes are inferred, not certain:
- Propose, then confirm. Never write a change until the operator approves that specific change for that specific source.
- Snapshot before any write. The pre-change row is the only way back.
- One source at a time. "Heal all" iterates and re-confirms each source.
- Never modify
active,name, oridentifier. Activation is an operator decision; identity changes break references. You only ever touchurl,rss_url, andconfig. - Never invent URLs. Only use URLs you actually observed in probe output
(RSS sample links, sitemap entries, redirect targets). A guessed
post_url_regexor domain silently breaks collection. - Merge config, don't replace it. Read the existing
config, change only the keys the fix requires, write the merged result back. - Bound the effort. At most 3 fix attempts per source. If the same class of failure survives 3 attempts, report it as a platform limitation rather than trying more permutations — some problems (bot protection, code bugs) cannot be fixed by config.
- DB is runtime truth. Write fixes to the database.
config/sources.yamlis only a new-build seed; it will drift and that is expected. Offer a YAML patch only as an optional final step, defaulting to skip.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 231 lines · 155 tokens per session scan A 09ba383f12fa
source-healing is a skill published in the GitHub repository dfirtnt/Huntable-CTI-Studio (11 stars, last pushed 3d ago), licensed MIT. It adds 155 tokens to every session and 2,415 once invoked, about $0.0008 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.
Other skills, from other repositories
configuring-windows-event-logging-for-detection
Configures Windows Event Logging with advanced audit policies to generate high-fidelity security events for threat detection and forensic investigation. Use when enabling audit policies for logon events, process creation, privilege use, and object access to feed SIEM detection rules. Activates for requests involving…
Blue Team Defense & Hardening
System hardening, detection engineering, security baseline monitoring, patch management, defense-in-depth architecture, and security posture improvement.
analyzing-ransomware-encryption-mechanisms
Analyzes encryption algorithms, key management, and file encryption routines used by ransomware families to assess decryption feasibility, identify implementation weaknesses, and support recovery efforts. Covers AES, RSA, ChaCha20, and hybrid encryption schemes. Activates for requests involving ransomware…
analyzing-slack-space-and-file-system-artifacts
Examine file system slack space, MFT entries, USN journal, and alternate data streams to recover hidden data and reconstruct file activity on NTFS volumes.
conducting-external-reconnaissance-with-osint
Conducts external reconnaissance using Open Source Intelligence (OSINT) techniques to map an organization's external attack surface without directly interacting with target systems. The tester gathers information from public sources including DNS records, certificate transparency logs, search engines, social media…
conducting-mobile-app-penetration-test
Conducts penetration testing of iOS and Android mobile applications following the OWASP Mobile Application Security Testing Guide (MASTG) to identify vulnerabilities in data storage, network communication, authentication, cryptography, and platform-specific security controls. The tester performs static analysis of…