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/rickywo/formic/declarenpx skills add rickywo/Formic --skill declaregit clone --depth 1 https://github.com/rickywo/FormicWrote 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/rickywo/formic/declare)<a href="https://agentmods.dev/skills/rickywo/formic/declare"><img src="https://agentmods.dev/badge/skills/rickywo/formic/declare.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 | $0.00021 | $0.00464 |
| Opus 5 | $0.00010 | $0.00232 |
| Sonnet 5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
declare 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.
What it actually says
Declare Skill - Upfront File Declaration
You are analyzing a task's implementation plan to determine which files will be created or modified during execution.
Task Title: $TASK_TITLE
Task Documentation: $TASK_DOCS_PATH
Output Location: $TASK_DOCS_PATH/declared-files.json
Instructions
-
Read the task's planning documents:
$TASK_DOCS_PATH/README.md- Feature specification$TASK_DOCS_PATH/PLAN.md- Implementation plan$TASK_DOCS_PATH/subtasks.json- Structured subtask list
-
Analyze the plan to identify ALL files that will be:
- Created (new files)
- Modified (existing files that will be changed)
-
Classify each file as either:
- exclusive: Files that only this task should modify (most files)
- shared: Common hotspot files that multiple tasks may need to modify concurrently. These include:
package.jsontsconfig.jsonsrc/types/index.ts- Route registration files (e.g.,
src/server/index.ts) - Configuration files
-
Write the output to
$TASK_DOCS_PATH/declared-files.jsonwith this exact schema:
{
"exclusive": [
"src/server/services/newService.ts",
"src/server/routes/newRoute.ts"
],
"shared": [
"package.json",
"src/types/index.ts"
]
}
Guidelines
- Be thorough - include ALL files that might be touched
- Use relative paths from the project root
- When in doubt, classify a file as exclusive (safer)
- Common shared/hotspot files:
package.json,tsconfig.json,src/types/index.ts,src/server/index.ts - Test files should be classified as exclusive
- New files (that don't exist yet) should be exclusive
Output
Write ONLY the declared-files.json file to the specified path. Do not modify any other files.
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 · 69 lines · 21 tokens per session scan A effc2c7269de
declare is a skill published in the GitHub repository rickywo/Formic (41 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 464 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
sprint-planning
Plan implementation sprints with story selection, goal definition, and execution ordering.
kanban-management
Initialize and manage Kanban board state for feature workflow tracking.
groom-backlog
Groom a project backlog in an issue tracker. Loads the whole board in bulk, computes a gap inventory instead of eyeballing one, verifies each candidate issue's factual claims against the code and the tracker, ranks the verified candidates by a stated four-tier heuristic, proposes an evidence-backed closure for an…
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…
trello-handoff
Move the current Trello card through the configured Symphony-for-Trello lifecycle. Use when picking up work, handing off for human review, marking a blocker, or completing a merge.
swarm-flow
The SDLC router — figures out where a project stands and runs the right phase. Use at the START of any work in a SwarmVault project: continuing/resuming a project, starting a new one, "what's next", or before writing any feature code, spec, design, or ticket. Also use when unsure which phase (requirements, design…