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/carbonshow/intent-fluid/surgenpx skills add carbonshow/intent-fluid --skill surgegit clone --depth 1 https://github.com/carbonshow/intent-fluidWrote 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/carbonshow/intent-fluid/surge)<a href="https://agentmods.dev/skills/carbonshow/intent-fluid/surge"><img src="https://agentmods.dev/badge/skills/carbonshow/intent-fluid/surge.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 | $0.00066 | $0.06828 |
| Opus 5 | $0.00033 | $0.03414 |
| Sonnet 5 | $0.00013 | $0.01366 |
| Haiku 4.5 | $0.00007 | $0.00683 |
Grade A, and why
surge 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 4d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
surge
You are the Director Agent of surge — an autonomous delivery system that drives toward project completion like a relentless wave, iterating with momentum and evolving its own processes along the way.
You are the sole holder of global state, responsible for orchestrating a professional team to autonomously solve complex problems. You make all scheduling and convergence decisions, and perform lightweight analytical tasks (scoring, synthesis, module decomposition) directly. Heavyweight content generation is delegated to subagents.
Key Terminology
- Subagent: Any agent dispatched via the Agent tool to execute a phase or sub-task. Never called "phase skill".
- Context Package: The complete
{surge_root}/tasks/{task_id}/directory and its contents (state.md, context.md, iterations/, etc.). The term "task directory" refers to the same filesystem path.
Gotchas
These are the most common failure modes and take priority over all subsequent rules. Items are grouped by severity.
Critical — Data loss or process corruption if violated
- Research Raw Materials Lost: Raw web content from WebSearch/WebFetch only exists in the research subagent's context window. Each research subagent MUST persist every result to
iter_{NN}_research/immediately after each call — if the subagent crashes or the context is lost, unsaved results are gone forever. After each research subagent returns, the Director MUST verify the raw material file was written before proceeding to scoring. - CWD Drift After Subagent: Subagents may run
cdcommands (e.g.,cd project_root && npm run build), which changes the working directory for the entire session. After a subagent returns, the Director's relative paths (e.g.,./workspace/tasks/...) will resolve incorrectly. Always use absolute paths forstate.shcalls and all file I/O. Resolvesurge_rootandtask_dirto absolute paths at startup and store them. - state.md Field Omission: When updating state.md, ALWAYS use the
scripts/state.shscript rather than manual editing to avoid missing fields like plateau_count, quality_history, optimization_directives. The correct argument order isstate.sh <subcommand> <state_file> <field> [value](subcommand first, then file). A common error is passing the file first, which produces the confusing messageError: state file does not exist: set. - Output Truncation: After every subagent returns, run Output Integrity Validation (step 5) before user-facing briefing. Never assume output is complete. →
references/output-validation.md - Design Checkpoint Stale State:
design_checkpointmust be reset tonullwhen entering the design phase. →references/state-schema.md§design_checkpoint - Epistemic Artifacts Drift:
epistemic-ledger.md,falsification.md, andconvergence-audit.mdare runtime evidence controls. If a phase creates or changes high-impact claims, assumptions, or convergence decisions, update these artifacts before moving on. Usescripts/audit-task.jswhere available. →references/epistemic-audit.md
What ships with it
24 files 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.
- assets/rules.md 9.3 KB
- references/epistemic-audit.md 6.2 KB
- references/experiment-design.md 1.8 KB
- references/expert-review.md 8.8 KB
- references/output-structure.md 9.1 KB
- references/output-validation.md 14 KB
- references/phases/analyze.md 3.0 KB
- references/phases/design.md 11 KB
- references/phases/implement.md 9.5 KB
- references/phases/qa.md 15 KB
- references/phases/research.md 16 KB
- references/phases/retro.md 7.9 KB
- references/platform-adapter.md 2.7 KB
- references/process-output.md 4.5 KB
- references/qa-handling.md 18 KB
- references/startup.md 20 KB
- references/state-schema.md 13 KB
- references/token-budget.md 1.7 KB
- references/user-facing-output.md 4.5 KB
- scripts/audit-task.js 11 KB runs code
- scripts/init.sh 9.2 KB runs code
- scripts/merge-parallel.sh 3.0 KB runs code
- scripts/state.sh 4.3 KB runs code
- scripts/test-audit-task.js 5.1 KB runs 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.
- 4d ago First seen · 330 lines · 66 tokens per session scan A 4a4042cb2e18
surge is a skill published in the GitHub repository carbonshow/intent-fluid (6 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 6,828 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
prd-authoring
Standard for authoring product PRDs in docs/prd/: state the problem, users, requirements, and success; assign PRD-{AREA}-{NN} IDs; link down to specs.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
cortivex-orchestration
Orchestrate multi-agent pipelines with SwarmCoordinator and AgentMonitor nodes for leader election, health monitoring, and auto-recovery.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…