Borrowing it
Nothing to install: this file belongs to optave/ops-codegraph-tool. 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/optave/ops-codegraph-tool/main/.claude/skills/titan-forge/SKILL.mdgit clone --depth 1 https://github.com/optave/ops-codegraph-toolWrote 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/optave/ops-codegraph-tool/titan-forge)<a href="https://agentmods.dev/skills/optave/ops-codegraph-tool/titan-forge"><img src="https://agentmods.dev/badge/skills/optave/ops-codegraph-tool/titan-forge/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/optave/ops-codegraph-tool/titan-forge"><img src="https://agentmods.dev/badge/skills/optave/ops-codegraph-tool/titan-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 170 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- high Anti-Refusal · line 220 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Tool Misuse · line 335 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 21 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 351 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00036 | $0.04134 |
| Opus 5.5 | $0.00014 | $0.01654 |
| Sonnet 5.5 | $0.00007 | $0.00827 |
| Haiku 4.5 | $0.00004 | $0.00413 |
Grade A, and why
titan-forge 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 2mo 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Titan FORGE — Execute Sync Plan
You are running the FORGE phase of the Titan Paradigm.
Your goal: read sync.json, find the next incomplete execution phase, make the actual code changes for each target, validate with /titan-gate, commit, and advance state.
Context budget: One phase per invocation. Do not attempt all phases in one session — the context window will fill. Run one phase, report, stop. User re-runs for the next phase.
Arguments (from $ARGUMENTS):
- No args → run next incomplete phase
--phase N→ jump to specific phase--target <name>→ run single target only (for retrying failures)--dry-run→ show what would be done without changing code--yes→ skip confirmation prompt (typically passed by/titan-runorchestrator)
Step 0 — Pre-flight
-
Worktree check:
git rev-parse --show-toplevel && git worktree listIf not in a worktree, stop: "Run
/worktreefirst." -
Sync with main (conditional):
git fetch origin main behind=$(git rev-list HEAD..origin/main --count)-
If
behind == 0→ already up to date, skip the merge entirely and print "Already up to date with origin/main." -
If
behind > 0→ merge:git merge origin/main --no-editIf there are merge conflicts, stop: "Merge conflict detected. Resolve conflicts and re-run
/titan-forge."After a successful merge, run a duplicate-commit check to detect re-applied work:
git log origin/main..HEAD --no-merges --format="%s" | sort | uniq -dIf any subjects are duplicated, print a warning listing them: "WARNING: Duplicate commit subjects found after merge — prior work may have been re-applied. Step 5 will auto-recover completed targets from git log so they are skipped." Do not stop — proceed to Step 3.
-
-
Load artifacts. Read:
.codegraph/titan/sync.json— execution plan (if missing: "Run/titan-syncfirst.").codegraph/titan/titan-state.json— current state.codegraph/titan/gauntlet.ndjson— per-target audit details.codegraph/titan/gauntlet-summary.json— aggregated results
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.
- 2mo ago First seen · 352 lines · 36 tokens per session scan A 94f7ee2f7c55
titan-forge is a skill published in the GitHub repository optave/ops-codegraph-tool (99 stars, last pushed 5d ago), licensed Apache-2.0. It adds 36 tokens to every session and 4,134 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
git-commit
Analyze changes with Git only and auto-generate conventional commit messages with optional emoji; suggests splitting commits when needed, runs local Git hooks by default (use --no-verify to skip).
git-master
MUST USE for ANY git operations: atomic commits, rebase/squash/fixup, and history search (blame, bisect, log -S, reflog). Load it before running git yourself, or pass loadskills=['git-master'] to the task that commits. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims and hook env vars, pre-commit framework migration, Starlark git.sandbox checks and unstaged fixes, signed commits, managed workdirs, fork-PR trust gate (clone gate and posting gate), and auth via identities or…
conventional-commit
Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.