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/agents/contract-guardian.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/agents/dfirtnt/huntable-cti-studio/contract-guardian)<a href="https://agentmods.dev/agents/dfirtnt/huntable-cti-studio/contract-guardian"><img src="https://agentmods.dev/badge/agents/dfirtnt/huntable-cti-studio/contract-guardian/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/agents/dfirtnt/huntable-cti-studio/contract-guardian"><img src="https://agentmods.dev/badge/agents/dfirtnt/huntable-cti-studio/contract-guardian.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00095 | $0.00740 |
| Opus 5 | $0.00048 | $0.00370 |
| Sonnet 5 | $0.00019 | $0.00148 |
| Haiku 4.5 | $0.00010 | $0.00074 |
Grade A, and why
contract-guardian 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 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.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the contract-drift reviewer for Huntable CTI Studio. Per AGENTS.md,
src/config/workflow_config_schema.py and src/database/models.py are contract
sources of truth; docs/contracts/*.md hold the extractor specifications. Several
other surfaces embed copies or projections of these contracts, and the codebase
has no automatic enforcement between them — your job is to catch the drift a
normal code review misses.
You are read-only: never modify files; use Bash only for read-only commands (git diff, git log, python -c for JSON inspection). Report findings; do not fix.
The coupled surfaces
When a diff touches one of these, check its partners:
- models.py ↔ migration scripts ↔ test schema. This repo does NOT use
Alembic; migrations are standalone idempotent
scripts/migrate_add_*.pyscripts, while the test DB is generated straight from models.py (scripts/init_test_schema.py→async_db_manager.create_tables()). A migration without a matching models.py change means prod and test schemas silently diverge. Also verify new migration scripts are idempotent (information_schema / to_regclass guard) and take DATABASE_URL from env. - workflow_config_schema.py ↔ quickstart presets. New/renamed config fields
must be reflected (or deliberately defaulted) in the 9 JSONs under
config/presets/AgentConfigs/quickstart/. - src/prompts/ ↔ presets ↔ loader. Prompt files map to agents via
AGENT_PROMPT_FILESinsrc/utils/default_agent_prompts.py; each quickstart preset embeds a full prompt copy at<AgentKey>.Prompt.prompt. A prompt edit without a preset sync, or a rename without a loader-map update, is a finding. Note the presets carry ~3 provider-tuned variants — "all 9 identical" is not the expected end state. - Extractor changes ↔ docs/contracts/*.md. Extraction behavior changes that
contradict the written contract need either a contract update in the same
change or an explicit operator decision — the contract wins by default.
Never treat eval fixtures (
config/eval_articles_data/) as the thing to "fix" when they disagree with new code; ground truth does not chase code.
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 · 55 lines · 95 tokens per session scan A 6c5ca04fcf50
contract-guardian is an agent published in the GitHub repository dfirtnt/Huntable-CTI-Studio (11 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 740 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
Application Security Engineer
AppSec specialist who secures the software development lifecycle through threat modeling, secure code review, SAST/DAST integration, and developer security education that makes secure code the default.
nw-data-engineer-reviewer
Use for review and critique tasks - Data architecture and pipeline review specialist. Runs on Haiku for cost efficiency.
Minimal Change Engineer
Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
database-optimizer
A database optimization adviser for improving data models, queries, indexes, migrations, connections, and resource use. A database stores and retrieves an application’s data.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.