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/vmobifystudio/app-dev-team/intent-tracenpx skills add vmobifystudio/app-dev-team --skill intent-tracegit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/vmobifystudio/app-dev-team/intent-trace)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/intent-trace"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/intent-trace.svg" alt="Measured on agentmods" 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 | $0.00107 | $0.02296 |
| Opus 5 | $0.00053 | $0.01148 |
| Sonnet 5 | $0.00021 | $0.00459 |
| Haiku 4.5 | $0.00011 | $0.00230 |
Grade A, and why
intent-trace 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 today.
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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent trace
This team writes the PRD, derives acceptance criteria from its own PRD, implements against its own spec, and tests against its own criteria. It can prove conformity to its interpretation and nothing else. If the interpretation drifted, everything downstream is consistently, verifiably, greenly wrong.
Nothing in here fixes that by being read. It fixes it by making the derivation nameable: every node says where it came from and who checks it, and two scripts fail when the chain does not hold.
1. The founder record — docs/00-founder-intent/
The original brief, transcripts, examples, competitor references and constraints exactly as received. Derived documents evolve; this one does not.
docs/00-founder-intent/
README.md what this directory is, copied from the plugin
brief.md the founder's words, verbatim, dated
transcript-<date>.md a conversation, pasted whole
example-<name>.<ext> a screenshot, a competitor link, a spreadsheet they sent
constraints.md budget, deadline, platform, legal, "never do X"
decisions.md append-only founder decisions (see §5)
MANIFEST.sha256 the tamper record — written by scripts/founder-intent.mjs
Rules:
- Append-only. Correcting the founder's words is not editing, it is losing the only external
oracle the team has. A changed mind is a new dated entry in
decisions.md, never an edit. - Verbatim. Summarised intent is interpreted intent, which is the thing being guarded against.
- Every material scope decision points here. A goal with no source in this directory is a goal
the team invented —
trace.mjsreports it asgoal_no_founder_source. - Thin is a finding, not a pass. A one-line brief cannot support a PRD;
product-validatorreturnsINTENT: CANNOT EVALUATEand says what is missing.
The tamper check:
node "${CLAUDE_PLUGIN_ROOT}/scripts/founder-intent.mjs" --write # record new files (refuses to re-record a changed one)
node "${CLAUDE_PLUGIN_ROOT}/scripts/founder-intent.mjs" # check: 0 clean · 1 tampered · 2 no record to check
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.
- today First seen · 159 lines · 107 tokens per session scan A cb72a1e5625c
intent-trace is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 24d ago), licensed MIT. It adds 107 tokens to every session and 2,296 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 2026-09-03.
Other skills, from other repositories
seeds-issue-audit
Audit and triage open Seeds (sd) issues — find which can be closed, auto-close high-confidence completed ones, and report borderline cases. Activate for prompts like "audit open issues", "which seeds issues can be closed", "clean up the issue tracker", "triage the seeds backlog".
good-first-issue-batch
File a batch of contributor-ready GitHub issues from the seeds backlog, re-verifying every candidate against HEAD first so no dead issue reaches a contributor. Activate for prompts like "file some good first issues", "open a batch of GFIs", "publish backlog issues to GitHub", "find contributor-ready work", or after an…
warren-dogfood-pipeline
Full prioritize → dispatch → shepherd → track pipeline against the live warren instance. Audits the seeds backlog around a focus theme, dispatches the surviving issues to warren agents one at a time, babysits the resulting PRs to merge (update-branch, conflict-repair runs, auto-merge), and closes the loop in the…
run
Conduct a task end to end, from a one-line fix to a multi-day programme - a short interview, then autonomous execution to the finish. Classifies the task S/M/L/XL, configures itself to the repo, routes each role to a cost tier, drives the agent team from the kanban board, and stops only at genuine decisions. Use for…
status
Where is the work right now. Regenerates the projections and the kanban board from the journal and answers with the progress line, the agents still running, the open gates and the resume steps. Read-only. Use for /tyran:status or when asked what is going on.
heartbeat
This skill should be used when the user asks to "run a heartbeat", "run the agent loop", "process GitHub issues", "check for work", or runs the /heartbeat command. Executes the WoterClip heartbeat — picks up GitHub issues, resolves personas, does work, and reports back.