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 skills add nirecom/agents --skill survey-historygit clone --depth 1 https://github.com/nirecom/agentsWrote 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/nirecom/agents/survey-history)<a href="https://agentmods.dev/skills/nirecom/agents/survey-history"><img src="https://agentmods.dev/badge/skills/nirecom/agents/survey-history/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nirecom/agents/survey-history"><img src="https://agentmods.dev/badge/skills/nirecom/agents/survey-history.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.01184 |
| Opus 5 | $0.00018 | $0.00592 |
| Sonnet 5 | $0.00007 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
survey-history 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 9d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate the project's git history and GitHub issue/PR timeline to detect changes made after the relevant issue was opened that might invalidate its premises.
Procedure
Apply skills/_shared/resolve-plans-dir.md once at the start of Procedure;
substitute the resolved absolute path for every <PLANS_DIR> placeholder
below. Reuse across all subsequent steps — do not re-resolve.
When invoked as a parallel Agent subagent by workflow-init, the orchestrator
passes artifact_path and context_path as resolved absolute strings — use
those instead.
SH-1. Input and issue number resolution:
Input precedence (read whichever exists first):
(a) <PLANS_DIR>/<session-id>-intent.md — preferred (post-clarify-intent calls)
(b) <PLANS_DIR>/<session-id>-context.md — fallback (pre-clarify-intent calls
from workflow-init)
Issue number N:
- From intent.md: extract from
## Issuessection (canonical parser:hooks/lib/parse-closes-issues.js). - From context.md: read
issue-numberfrom## Session metadata. - If N is
(none), absent, or non-integer → proceed in keyword-only mode (Step SH-3).
SH-2. Run: gh issue view <N> --json createdAt --jq .createdAt
- On success: record
openedAt(ISO-8601 date string). - On failure (gh unavailable, auth error, etc.): record "gh unavailable — using
approximate date" and continue; set
openedAtto 90 days ago as a conservative fallback.
SH-3. Keyword-only mode (no issue number available): run bash "$AGENTS_CONFIG_DIR/skills/survey-history/scripts/keyword-only-mode.sh" and follow the procedure it outputs.
After writing the artifact (Step SH-6), stop. Do NOT invoke make-outline-plan.
SH-4. Run the following three investigations in parallel:
a. Git log since issue opened:
git log --since=<openedAt> --pretty=format:"%h %ad %s" --date=short
b. Run bash "$AGENTS_CONFIG_DIR/skills/survey-history/scripts/history-docs-search.sh" --since <openedAt> and follow the procedure it outputs.
c. Merged PRs since issue opened:
gh pr list --state merged --search "merged:>=<openedAt>" --limit 20 --json number,title,mergedAt
On gh failure: record "gh pr list unavailable" and continue.
SH-5. Relevance scoring: Extract keywords from intent.md Background/Motivation and Scope (≥4 characters, excluding stop words: the, and, for, with, that, this, from, into, have, been). Score each commit/PR subject by keyword match count. Keep: score ≥ 1 entries, plus the top 5 by score regardless of threshold.
SH-6. Run bash "$AGENTS_CONFIG_DIR/skills/survey-history/scripts/artifact-template.sh" to get the output format,
then write <PLANS_DIR>/<session-id>-survey-history.md following that format.
The ## Candidate class members section lists sibling members identified
from git history and history.md (per rules/core-principles.md CPR-E2C Elevate
to the Class). Each member is two lines: (a) name + description + commit/history-entry reference;
(b) proposed triage: value and 1-line rationale grounded in historical evidence.
Triage values: proposed triage: MUST (symmetric change required for class
consistency), proposed triage: OPTIONAL (related but independently fixable),
proposed triage: NA (orthogonal sibling, no fix needed). When uncertain,
propose OPTIONAL. If no candidates are detected, write - (none detected).
This section is required even in DEGRADED MODE or keyword-only mode.
If gh was unavailable, note it at the top of the file under a ## Data gaps section.
What ships with it
3 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.
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.
- 9d ago First seen · 89 lines · 36 tokens per session scan A 6e38d8a2f473
survey-history is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,184 once invoked, about $0.0002 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.