PLATFORM FEATURESCoding Agent

Coding Agent

16 min read

Implement approved user stories in your linked Git repo — configure runs, batch Implement All, context, tokens, and Insights.

Coding Agent

Coding Agent implements your approved user stories directly in your linked Git repository — without you leaving Forge. It clones your repo, reads your full journey context (architecture, PRD, acceptance criteria), writes the code, and pushes a branch with a pull request ready to review.

You pick the story. Forge does the implementation.

Prefer interactive control? Use with the same stories and Suggested AI Models.


What You Get

OutcomeWhat you get
Code implementedAgainst your linked Git repo
Dedicated branchforge/wo-{id} — pushed automatically
Pull requestOpened when your provider allows
Live logsStreaming as the agent works
Full traceabilityRuns tied to the story with reports and logs

Before You Start

Three things must be in place before Coding Agent will run:

1. Application Context saved

Your project must have stories under Application Context → Stories.

2. Repository linked

Link a repo under the ALM Repos tab using a Git connector with the full repository name. A URL-only link is not enough — the connector must have push and PR create permissions.

3. Story is coding-eligible

Stories marked as manual-only do not show the Coding Agent tab.


Run Coding Agent on a Story

Step 1 — Open the story

Go to Application Context → Stories → open the story you want to implement.

Step 2 — Open the Coding Agent tab

Click the Coding Agent tab on the story, or use the card menu → Run Coding Agent.

Step 3 — Configure the run

FieldWhat it does
RepositoryThe linked repo Forge will clone and push to
Instructions for AIOne-off guidance for this run only (~2000 chars)
Commit Prefix (Advanced)e.g. JIRA-123 prepended to commit messages
Skip testing (Advanced)Skips the test phase — only use if CI will still gate the PR
Skip code review (Advanced)Skips the AI review phase
Base Branch (Advanced)The branch Forge forks from

Review the token estimate shown — this is a planning guide, not a bill.

Step 4 — Click Implement with Coding Agent

The agent starts. You'll see:

  • Status: Coding Agent Running
  • Live Logs streaming in real time — file reads, commands, AI reasoning as it works
  • Cancel Execution button if you need to stop the run

Closing the tab does not stop the run. Reopen it to reconnect to an active session.

Step 5 — Review the result

When finished, the result panel shows one of: PR Created, Changes Pushed, or Implementation Complete.

From here you can:

ActionWhere
Open the pull requestView Pull Request
See phases, AC coverage, files changedResult panel
Download evidenceDownload Report / Download Logs
Run againRun Again — prior runs are listed in the configure view

The branch in GitHub will show as forge/wo-{id} with the commit message [WO-XXX] Story title — pushed by the Forge Coding Agent.


What Context the Agent Uses

The agent does not start from a blank prompt. Each run assembles:

SourceHow it is used
User storyTitle, description, acceptance criteria, priority, points
ArchitectureApproved architecture options from the journey
PRD / BRDProduct and business requirements context
UI DesignPage and layout summary when UI Design was approved
RepositoryLive clone of the linked repo at the base branch you select
Coding Agent InstructionsPersisted per-story guidance set on the story Details tab
Instructions for AIOne-off extras added at launch for this run only
Prior feedbackPrevious run or council feedback when available

Persist Instructions vs One-Off Instructions

Coding Agent Instructions (story Details tab) — saved permanently on the story. Applied on every run including retries and batch. Use this for scope rules, file paths to avoid, or coding standards that should always apply.

Instructions for AI (launcher) — applies to this run only. Use for temporary overrides or one-time context.


Run on Multiple Stories — Implement All

When several stories are ready, use batch mode instead of running them one by one.

Step 1 — Open batch mode

Stories toolbar → Implement AllBatch Coding Agent

Step 2 — Select stories

Use Select All ({n} actionable) or pick individually. Batch automatically skips stories that are completed, removed, in review, blocked, or marked manual-only. If a selected story has unresolved dependencies, batch can auto-include the blocking stories.

Step 3 — Choose a mode

ModeUse when
Sequential (respects dependencies)Stories block each other — safer default
Parallel (concurrent)Stories are fully independent — faster

Step 4 — Review and launch

Review the story list, estimated duration, and token estimate. Click Implement with Coding Agent ({n} Stories).

You can minimize the batch panel — it continues in the background. Go to Insights → Coding Agent to watch live logs for any story in the batch.

If the batch fails partway through, use Resume Remaining to continue from where it stopped, or Start Fresh to rerun everything. Download the batch report at any time.


Token Estimates

Shown on the story Details tab, the single-story launcher, and the Implement All panel.

Estimates are calculated from prior coding-agent analytics scaled by story complexity — low (0.6×), medium (1.0×), high (1.5×) — or a platform baseline when no history exists. Actual usage varies with repo size, number of retries, and whether testing and review phases run.

Platform admins can see realized token counts and cost in Insights and run results.


Insights

Track Coding Agent activity per project under Application Context → Insights → Coding Agent.

MetricWhat it means
Total RunsAll executions — succeeded and failed
Success RatePercentage of successful runs; stories completed by the agent
Avg DurationMean runtime and average files changed per run
Remaining EstimateProjected work for stories not yet run

The Recent Executions list shows individual traces, diffs, reports, and a View Live Logs link for each run.

Empty: No Coding Agent Runs Yet. Platform admins: Admin → Observability → Coding Agent for cross-tenant views.


Suggested AI Models

On story Details, expand Suggested AI Models for Recommended and Budget Alternatives by complexity (low / medium / high).

For IDE / MCP only. The Forge Coding Agent launcher does not use this picker — the worker uses platform defaults.

MCP get_work_order / get_next_work_order include the same recommended_models. See .


Forge vs IDE

Coding Agent (Forge)Open in IDE / MCP
Best forHands-off and batch runsInteractive steering mid-implementation
WhereStory Coding Agent tab, Run Coding Agent, Implement AllOpen in IDE; MCP in Cursor / VS Code / etc.
Who writes codeForge workerYour local agent
ModelPlatform defaults (no launcher picker)You choose; Forge suggests via Suggested AI Models
Outputforge/wo-{id}, push, optional PR, report/logsCommits / PRs from your IDE workflow

Troubleshooting

SymptomWhat to try
No linked repositories foundRepos → link with connector + full name; Test the connector
Coding Agent tab missingStory may be manual-only (requires manual implementation)
AI timeout / AI errorSimplify Instructions for AI; Run Again
Test failureFix tests in a follow-up, or Skip testing if CI will still gate the PR
Auth / push / PR failedCheck connector permissions (push + PR create) and base branch
Batch stuck / partialResume Remaining or Start Fresh; check Insights live logs
Blank / stalled ProgressReopen the tab to reconnect; confirm workers are healthy
Unexpected files changedTighten Coding Agent Instructions (scope / paths to avoid)

Expand Why did it fail? on the result panel for category-specific hints.


Best practices

PracticeWhy
Persist rules in Coding Agent Instructions; use launcher text for one-offsConsistency across retries and batch
Prefer Sequential until dependencies are cleanAvoid blocked or out-of-order PRs
Link the repo your team already reviewsPRs land where reviewers already work
Start with smaller stories, then larger onesFaster feedback on agent quality
Skip testing only when CI still validatesDon't ship untested changes by accident
Use Open in IDE for messy, exploratory storiesHuman-in-the-loop when the path is unclear
Approve architecture (and UI Design when relevant) firstBetter context → better PRs

  • — Stories, Repos, Insights
  • — tenant-wide analytics (not per-project Coding Agent KPIs)
  • — IDE workflow + recommended_models
  • — capabilities, Figma, chat, upload, and .fig download
  • — GitHub / GitLab / Bitbucket