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.
npx agentmods add skills/sidcorp-co/forge/forge-fixnpx skills add SidCorp-co/forge --skill forge-fixgit clone --depth 1 https://github.com/SidCorp-co/forgeWhat 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 | $0.00097 | $0.01983 |
| Opus 5 | $0.00048 | $0.00992 |
| Sonnet 5 | $0.00019 | $0.00397 |
| Haiku 4.5 | $0.00010 | $0.00198 |
Grade A, and why
forge-fix 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Re-run the Step 4 reproduction first — confirm the failure is gone (regression test green / endpoint returns expected / screen behaves). Then: if the fix touches API endpoints, run real API tests (curl affected endpoints How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Fix
Applies scoped fixes based on review or QA rejection feedback. This is NOT a full reimplementation — it reads what failed, fixes only that, and re-submits.
The key discipline: fix what the feedback says, nothing more. Expanding scope during a fix cycle leads to new bugs and infinite review loops.
Usage
/forge-fix <documentId>
Tools
- forge_issues — get issue data, update status
- forge_comments — read rejection feedback, post fix summary
- forge_coolify_deploy — trigger deployment after push
- Codebase tools — Read, Edit, Write, Glob, Grep, Bash
Read references/fix-workflow.md for parsing rejection formats, branch handling, and fix strategy details.
Workflow
Pull-model note: On large issues
forge_step_startreturns a lean manifest (bodyTruncated:true). Fetchplan/description/acceptanceCriteriaas needed viaforge_issues.get { documentId, fields: ['plan'] }rather than assuming full body is present.
Step 1: Fetch Issue & Feedback
forge_issues → get → { documentId: "<id>" }
forge_comments → list → { filters: { issue: "<documentId>" } }
Verify status is reopen. Find the latest rejection comment — either:
- Code Review (starts with
## Code Review) — from forge-review, has severity table - QA Test Report (starts with
**QA Test Report**) — from forge-test, has pass/fail table
If feedback is unclear or missing → post clarifying comment, set needs_info, stop.
Step 2: Understand the Feedback
Parse the rejection:
- From review: extract Bug and Minor severity findings. Ignore Low items.
- From QA: extract FAIL test cases and failure descriptions.
Each finding = one fix task. Don't invent additional fixes.
Step 3: Confirm Branch & Check Out
First confirm current git state — in pipeline-resumed sessions the working tree may be on an unexpected branch:
git branch --show-current
git status
If dirty, stash or clean before switching. Then check out the ISS-* branch. The feature branch is always kept alive through the pipeline (forge-release merges it to production at the end):
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.
- 2d ago First seen · 171 lines · 97 tokens per session scan A f59b30ed2a17
forge-fix is a skill published in the GitHub repository SidCorp-co/forge (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,983 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
ad-creative
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
adaptive-anti-bot-web-scraping
Adaptive web scraping framework with anti-bot bypass and spider crawling.
ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test…
access-gevety-health-biomarker-data
Access your Gevety health data - biomarkers, healthspan scores, biological age, supplements, activities, daily actions, 90-day health protocol, and upcoming tests.
access-exchange-2010-ews-functions
Exchange 2010 EWS integration for emails, calendar, contacts, and tasks.